It can be hard to stay up-to-date on the published papers in
the field of adversarial examples,
where we have seen massive growth in the number of papers
written each year.
I have been somewhat religiously keeping track of these
papers for the last few years, and realized it may be helpful
for others to release this list.
The only requirement I used for selecting papers for this list
is that it is primarily a paper about adversarial examples,
or extensively uses adversarial examples.
Due to the sheer quantity of papers, I can't guarantee
that I actually have found all of them.
But I did try.
I also may have included papers that don't match
these criteria (and are about something different instead),
or made inconsistent
judgement calls as to whether or not any given paper is
mainly an adversarial example paper.
Send me an email if something is wrong and I'll correct it.
As a result, this list is completely un-filtered.
Everything that mainly presents itself as an adversarial
example paper is listed here; I pass no judgement of quality.
For a curated list of papers that I think are excellent and
worth reading, see the
Adversarial Machine Learning Reading List.
One final note about the data.
This list automatically updates with new papers, even before I
get a chance to manually filter through them.
I do this filtering roughly twice a week, and it's
then that I'll remove the ones that aren't related to
adversarial examples.
As a result, there may be some
false positives on the most recent few entries.
The new un-verified entries will have a probability indicated that my
simplistic (but reasonably well calibrated)
bag-of-words classifier believes the given paper
is actually about adversarial examples.
The full paper list appears below. I've also released a
TXT file (and a TXT file
with abstracts) and a
JSON file
with the same data. If you do anything interesting with
this data I'd be happy to hear from you what it was.
Paper List
2024-12-02
Traversing the Subspace of Adversarial Patches. (83%)Jens Bayer; Stefan Becker; David Münch; Michael Arens; Jürgen Beyerer
DiffPatch: Generating Customizable Adversarial Patches using Diffusion Model. (82%)Zhixiang Wang; Guangnan Ye; Xiaosen Wang; Siheng Chen; Zhibo Wang; Xingjun Ma; Yu-Gang Jiang
Exploring the Robustness of AI-Driven Tools in Digital Forensics: A Preliminary Study. (74%)Silvia Lucia Sanna; Leonardo Regano; Davide Maiorca; Giorgio Giacinto
Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios. (69%)Sangyeon Yoon; Wonje Jeung; Albert No
Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior. (67%)Yi Yu; Yufei Wang; Wenhan Yang; Lanqing Guo; Shijian Lu; Ling-Yu Duan; Yap-Peng Tan; Alex C. Kot
Adversarial Attacks on Hyperbolic Networks. (26%)Spengler Max van; Jan Zahálka; Pascal Mettes
CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models. (10%)Zhixiang Guo; Siyuan Liang; Aishan Liu; Dacheng Tao
R.I.P.: A Simple Black-box Attack on Continual Test-time Adaptation. (5%)Trung-Hieu Hoang; Duc Minh Vo; Minh N. Do
Precision Profile Pollution Attack on Sequential Recommenders via Influence Function. (1%)Xiaoyu Du; Yingying Chen; Yang Zhang; Jinhui Tang
2024-12-01
Intermediate Outputs Are More Sensitive Than You Think. (61%)Tao Huang; Qingyu Huang; Jiayang Meng
Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection. (16%)Delong Zhu; Yuezun Li; Baoyuan Wu; Jiaran Zhou; Zhibo Wang; Siwei Lyu
Online Poisoning Attack Against Reinforcement Learning under Black-box Environments. (11%)Jianhui Li; Bokang Zhang; Junfeng Wu
2024-11-30
Hard-Label Black-Box Attacks on 3D Point Clouds. (99%)Daizong Liu; Yunbo Tao; Pan Zhou; Wei Hu
Exposing LLM Vulnerabilities: Adversarial Scam Detection and Performance. (69%)Chen-Wei Chang; Shailik Sarkar; Shutonu Mitra; Qi Zhang; Hossein Salemi; Hemant Purohit; Fengxiu Zhang; Michin Hong; Jin-Hee Cho; Chang-Tien Lu
Exact Certification of (Graph) Neural Networks Against Label Poisoning. (22%)Mahalakshmi Sabanayagam; Lukas Gosch; Stephan Günnemann; Debarghya Ghoshdastidar
Jailbreak Large Vision-Language Models Through Multi-Modal Linkage. (12%)Yu Wang; Xiaofei Zhou; Yichen Wang; Geyuan Zhang; Tianxing He
2024-11-29
Towards Class-wise Robustness Analysis. (99%)Tejaswini Medi; Julia Grabinski; Margret Keuper
FLARE: Towards Universal Dataset Purification against Backdoor Attacks. (81%)Linshan Hou; Wei Luo; Zhongyun Hua; Songhua Chen; Leo Yu Zhang; Yiming Li
Robust Table Integration in Data Lakes. (56%)Daomin Ji; Hui Luo; Zhifeng Bao; Shane Culpepper
On the Adversarial Robustness of Instruction-Tuned Large Language Models for Code. (38%)Md Imran Hossen; Xiali Hei
Parallel Stacked Aggregated Network for Voice Authentication in IoT-Enabled Smart Devices. (10%)Awais Khan; Ijaz Ul Haq; Khalid Mahmood Malik
Fusing Physics-Driven Strategies and Cross-Modal Adversarial Learning: Toward Multi-Domain Applications. (1%)Hana Satou; Alan Mitkiy
SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks. (1%)Kim-Celine Kahl; Selen Erkan; Jeremias Traub; Carsten T. Lüth; Klaus Maier-Hein; Lena Maier-Hein; Paul F. Jaeger
2024-11-28
SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments. (84%)Yue Cao; Yun Xing; Jie Zhang; Di Lin; Tianwei Zhang; Ivor Tsang; Yang Liu; Qing Guo
PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning. (69%)Shenghui Li; Edith C. -H. Ngai; Fanghua Ye; Thiemo Voigt
Random Sampling for Diffusion-based Adversarial Purification. (26%)Jiancheng Zhang; Peiran Dong; Yongyong Chen; Yin-Ping Zhao; Song Guo
Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models. (11%)Chung-Ting Tsai; Ching-Yun Ko; I-Hsin Chung; Yu-Chiang Frank Wang; Pin-Yu Chen
LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm. (2%)Dazhuang Liu; Yanqi Qiao; Rui Wang; Kaitai Liang; Georgios Smaragdakis
Enhancing Neural Network Robustness Against Fault Injection Through Non-linear Weight Transformations. (2%)Ninnart Fuengfusin; Hakaru Tamukoh
2024-11-27
Visual Adversarial Attack on Vision-Language Models for Autonomous Driving. (99%)Tianyuan Zhang; Lu Wang; Xinwei Zhang; Yitong Zhang; Boyi Jia; Siyuan Liang; Shengshan Hu; Qiang Fu; Aishan Liu; Xianglong Liu
Fall Leaf Adversarial Attack on Traffic Sign Classification. (99%)Anthony Etim; Jakub Szefer
Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment. (67%)Soumya Suvra Ghosal; Souradip Chakraborty; Vaibhav Singh; Tianrui Guan; Mengdi Wang; Ahmad Beirami; Furong Huang; Alvaro Velasquez; Dinesh Manocha; Amrit Singh Bedi
Neutralizing Backdoors through Information Conflicts for Large Language Models. (26%)Chen Chen; Yuchen Sun; Xueluan Gong; Jiaxin Gao; Kwok-Yan Lam
Hidden Data Privacy Breaches in Federated Learning. (22%)Xueluan Gong; Yuji Wang; Shuaike Li; Mengyuan Sun; Songze Li; Qian Wang; Kwok-Yan Lam; Chen Chen
SoK: Watermarking for AI-Generated Content. (3%)Xuandong Zhao; Sam Gunn; Miranda Christ; Jaiden Fairoze; Andres Fabrega; Nicholas Carlini; Sanjam Garg; Sanghyun Hong; Milad Nasr; Florian Tramer; Somesh Jha; Lei Li; Yu-Xiang Wang; Dawn Song
From Open Vocabulary to Open World: Teaching Vision Language Models to Detect Novel Objects. (1%)Zizhao Li; Zhengkang Xiang; Joseph West; Kourosh Khoshelham
2024-11-26
Adversarial Training in Low-Label Regimes with Margin-Based Interpolation. (99%)Tian Ye; Rajgopal Kannan; Viktor Prasanna
BadScan: An Architectural Backdoor Attack on Visual State Space Models. (98%)Om Suhas Deshmukh; Sankalp Nagaonkar; Achyut Mani Tripathi; Ashish Mishra
Stealthy Multi-Task Adversarial Attacks. (92%)Jiacheng Guo; Tianyun Zhang; Lei Li; Haochen Yang; Hongkai Yu; Minghai Qin
Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers. (82%)Fatemeh Nourilenjan Nokabadi; Jean-Francois Lalonde; Christian Gagné
MADE: Graph Backdoor Defense with Masked Unlearning. (82%)Xiao Lin amd Mingjie Li; Yisen Wang
Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models. (75%)Shuyang Hao; Bryan Hooi; Jun Liu; Kai-Wei Chang; Zi Huang; Yujun Cai
Privacy-preserving Robotic-based Multi-factor Authentication Scheme for Secure Automated Delivery System. (9%)Yang Yang; Aryan Mohammadi Pasikhani; Prosanta Gope; Biplab Sikdar
PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning. (2%)Zhen Sun; Tianshuo Cong; Yule Liu; Chenhao Lin; Xinlei He; Rongmao Chen; Xingshuo Han; Xinyi Huang
Multi-Objective Reinforcement Learning for Automated Resilient Cyber Defence. (1%)Ross O'Driscoll; Claudia Hagen; Joe Bater; James M. Adams
Improved Parallel Derandomization via Finite Automata with Applications. (1%)Jeff Giliberti; David G. Harris
2024-11-25
Unlocking The Potential of Adaptive Attacks on Diffusion-Based Purification. (99%)Andre Kassis; Urs Hengartner; Yaoliang Yu
Imperceptible Adversarial Examples in the Physical World. (99%)Weilin Xu; Sebastian Szyller; Cory Cornelius; Luis Murillo Rojas; Marius Arvinte; Alvaro Velasquez; Jason Martin; Nageen Himayat
Scaling Laws for Black box Adversarial Attacks. (99%)Chuan Liu; Huanran Chen; Yichi Zhang; Yinpeng Dong; Jun Zhu
Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack. (81%)Xide Xu; Muhammad Atif Butt; Sandesh Kamath; Bogdan Raducanu
UVCG: Leveraging Temporal Consistency for Universal Video Protection. (54%)KaiZhou Li; Jindong Gu; Xinchun Yu; Junjie Cao; Yansong Tang; Xiao-Ping Zhang
Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models. (50%)Songning Lai; Yu Huang; Jiayu Yang; Gaoxiang Huang; Wenshuo Chen; Yutao Yue
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing. (50%)Hanhui Wang; Yihua Zhang; Ruizheng Bai; Yue Zhao; Sijia Liu; Zhengzhong Tu
Sparse patches adversarial attacks via extrapolating point-wise information. (47%)Yaniv Nemcovsky; Avi Mendelson; Chaim Baskin
DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders. (10%)Sizai Hou; Songze Li; Duanyi Yao
RED: Robust Environmental Design. (10%)Jinghan Yang
BadSFL: Backdoor Attack against Scaffold Federated Learning. (3%)Xingshuo Han; Xuanye Zhang; Xiang Lan; Haozhao Wang; Shengmin Xu; Shen Ren; Jason Zeng; Ming Wu; Michael Heinrich; Tianwei Zhang
Why the Agent Made that Decision: Explaining Deep Reinforcement Learning with Vision Masks. (2%)Rui Zuo; Zifan Wang; Simon Khan; Garrett Ethan Katz; Qinru Qiu
XAI and Android Malware Models. (2%)Maithili Kulkarni; Mark Stamp
Revisiting Marr in Face: The Building of 2D--2.5D--3D Representations in Deep Neural Networks. (1%)Xiangyu Zhu; Chang Yu; Jiankuo Zhao; Zhaoxiang Zhang; Stan Z. Li; Zhen Lei
2024-11-24
Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks. (99%)Peng Xie; Yequan Bie; Jianda Mao; Yangqiu Song; Yang Wang; Hao Chen; Kani Chen
ExAL: An Exploration Enhanced Adversarial Learning Algorithm. (92%)A Vinil; Aneesh Sreevallabh Chivukula; Pranav Chintareddy
A Tunable Despeckling Neural Network Stabilized via Diffusion Equation. (64%)Yi Ran; Zhichang Guo; Jia Li; Yao Li; Martin Burger; Boying Wu
Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference. (10%)Depeng Chen; Hao Chen; Hulin Jin; Jie Cui; Hong Zhong
DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation. (2%)Ruiqiang Xiao; Songning Lai; Yijun Yang; Jiemin Wu; Yutao Yue; Lei Zhu
Stealth Attacks Against Moving Target Defense for Smart Grid. (2%)Ke Sun; Iñaki Esnaola; H. Vincent Poor
2024-11-23
Improving Transferable Targeted Attacks with Feature Tuning Mixup. (99%)Kaisheng Liang; Xuelong Dai; Yanjie Li; Dong Wang; Bin Xiao
Enhancing the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation. (99%)Fengfan Zhou; Bangjie Yin; Hefei Ling; Qianyu Zhou; Wenxuan Wang
Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment. (4%)Alvi Md Ishmam; Christopher Thomas
LoBAM: LoRA-Based Backdoor Attack on Model Merging. (2%)Ming Yin; Jingyang Zhang; Jingwei Sun; Minghong Fang; Hai Li; Yiran Chen
2024-11-22
Exploring the Robustness and Transferability of Patch-Based Adversarial Attacks in Quantized Neural Networks. (99%)Amira Guesmi; Bassem Ouni; Muhammad Shafique
Gradient Masking All-at-Once: Ensemble Everything Everywhere Is Not Robust. (99%)Jie Zhang; Kristina Nikolić; Nicholas Carlini; Florian Tramèr
Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks. (98%)Han Wang; Gang Wang; Huan Zhang
Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI. (45%)Won Jun Kim; Hyungjin Chung; Jaemin Kim; Sangmin Lee; Byeongsu Sim; Jong Chul Ye
Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Language Models. (41%)Wanqi Yang; Yanda Li; Meng Fang; Yunchao Wei; Tianyi Zhou; Ling Chen
Universal and Context-Independent Triggers for Precise Control of LLM Outputs. (31%)Jiashuo Liang; Guancheng Li; Yang Yu
Benchmarking the Robustness of Optical Flow Estimation to Corruptions. (13%)Zhonghua Yi; Hao Shi; Qi Jiang; Yao Gao; Ze Wang; Yufan Zhang; Kailun Yang; Kaiwei Wang
Twin Trigger Generative Networks for Backdoor Attacks against Object Detection. (4%)Zhiying Li; Zhi Liu; Guanggang Geng; Shreyank N Gowda; Shuyuan Lin; Jian Weng; Xiaobo Jin
Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning. (2%)Junjie Shan; Ziqi Zhao; Jialin Lu; Rui Zhang; Siu Ming Yiu; Ka-Ho Chow
Heavy-tailed Contamination is Easier than Adversarial Contamination. (1%)Yeshwanth Cherapanamjeri; Daniel Lee
Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage. (1%)Soumil Datta; Shih-Chieh Dai; Leo Yu; Guanhong Tao
Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach. (1%)Lars Nieradzik; Henrike Stephani; Janis Keuper
2024-11-21
Generating Realistic Adversarial Examples for Business Processes using Variational Autoencoders. (99%)Alexander Stevens; Jari Peeperkorn; Smedt Johannes De; Weerdt Jochen De
Learning Fair Robustness via Domain Mixup. (81%)Meiyu Zhong; Ravi Tandon
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs. (78%)Advik Raj Basani; Xiao Zhang
Adversarial Prompt Distillation for Vision-Language Models. (75%)Lin Luo; Xin Wang; Bojia Zi; Shihao Zhao; Xingjun Ma
AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection. (74%)Jialin Lu; Junjie Shan; Ziqi Zhao; Ka-Ho Chow
Indiscriminate Disruption of Conditional Inference on Multivariate Gaussians. (50%)William N. Caballero; Matthew LaRosa; Alexander Fisher; Vahid Tarokh
GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning. (4%)Jiani Zhu; Xi Lin; Yuxin Qi; Qinghua Mao
Global Challenge for Safe and Secure LLMs Track 1. (4%)Xiaojun Jia; Yihao Huang; Yang Liu; Peng Yan Tan; Weng Kuan Yau; Mun-Thye Mak; Xin Ming Sim; Wee Siong Ng; See Kiong Ng; Hanqing Liu; Lifeng Zhou; Huanqian Yan; Xiaobing Sun; Wei Liu; Long Wang; Yiming Qian; Yong Liu; Junxiao Yang; Zhexin Zhang; Leqi Lei; Renmiao Chen; Yida Lu; Shiyao Cui; Zizhou Wang; Shaohua Li; Yan Wang; Rick Siow Mong Goh; Liangli Zhen; Yingjie Zhang; Zhe Zhao
TrojanEdit: Backdooring Text-Based Image Editing Models. (3%)Ji Guo; Peihong Chen; Wenbo Jiang; Guoming Lu
Evaluating the Robustness of Analogical Reasoning in Large Language Models. (1%)Martha Lewis; Melanie Mitchell
Memory Backdoor Attacks on Neural Networks. (1%)Eden Luzon; Guy Amit; Roy Weiss; Yisroel Mirsky
2024-11-20
Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks. (98%)Yong Xie; Weijie Zheng; Hanxun Huang; Guangnan Ye; Xingjun Ma
TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models. (96%)Xin Wang; Kai Chen; Jiaming Zhang; Jingjing Chen; Xingjun Ma
Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning. (86%)Zhi Luo; Xiyuan Yang; Pan Zhou; Di Wang
A Survey on Adversarial Robustness of LiDAR-based Machine Learning Perception in Autonomous Vehicles. (86%)Junae Kim; Amardeep Kaur
Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation. (68%)Ke Wuhan University Zhao; Huayang Wuhan University Huang; Miao Wuhan University Li; Yu Wuhan University Wu
AI-generated Image Detection: Passive or Watermark? (22%)Moyang Guo; Yuepeng Hu; Zhengyuan Jiang; Zeyu Li; Amir Sadovnik; Arka Daw; Neil Gong
SoK: A Systems Perspective on Compound AI Threats and Countermeasures. (12%)Sarbartha Banerjee; Prateek Sahu; Mulong Luo; Anjo Vahldiek-Oberwagner; Neeraja J. Yadwadkar; Mohit Tiwari
CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models. (12%)Naen Xu; Changjiang Li; Tianyu Du; Minxi Li; Wenjie Luo; Jiacheng Liang; Yuyuan Li; Xuhong Zhang; Meng Han; Jianwei Yin; Ting Wang
Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors. (5%)Satoru Koda; Ikuya Morikawa
2024-11-19
NMT-Obfuscator Attack: Ignore a sentence in translation with only one word. (99%)Sahar Sadrizadeh; César Descalzo; Ljiljana Dolamic; Pascal Frossard
Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessment. (75%)Ekaterina Shumitskaya; Mikhail Pautov; Dmitriy Vatolin; Anastasia Antsiferova
When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations. (3%)Huaizhi Ge; Yiming Li; Qifan Wang; Yongfeng Zhang; Ruixiang Tang
2024-11-18
Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack. (99%)Nicole Meng; Caleb Manicke; David Chen; Yingjie Lao; Caiwen Ding; Pengyu Hong; Kaleel Mahmood
Adapting to Cyber Threats: A Phishing Evolution Network (PEN) Framework for Phishing Generation and Analyzing Evolution Patterns using Large Language Models. (87%)Fengchao Chen; Tingmin Wu; Van Nguyen; Shuo Wang; Hongsheng Hu; Alsharif Abuadbba; Carsten Rudolph
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning. (75%)Kichang Lee; Yujin Shin; Jonghyuk Yun; Jun Han; JeongGil Ko
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization. (67%)Nay Myat Min; Long H. Pham; Yige Li; Jun Sun
Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization. (50%)Mingda Zhang; Mingli Zhu; Zihao Zhu; Baoyuan Wu
Few-shot Model Extraction Attacks against Sequential Recommender Systems. (38%)Hui Zhang; Fu Liu
CLUE-MARK: Watermarking Diffusion Models using CLWE. (26%)Kareem Shehata; Aashish Kolluri; Prateek Saxena
The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models. (13%)Xikang Yang; Xuehai Tang; Jizhong Han; Songlin Hu
Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods. (8%)Egor Kovalev; Georgii Bychkov; Khaled Abud; Aleksandr Gushchin; Anna Chistyakova; Sergey Lavrushkin; Dmitriy Vatolin; Anastasia Antsiferova
2024-11-17
Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics. (86%)Taowen Wang; Dongfang Liu; James Chenhao Liang; Wenhao Yang; Qifan Wang; Cheng Han; Jiebo Luo; Ruixiang Tang
JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit. (47%)Zeqing He; Zhibo Wang; Zhixuan Chu; Huiyu Xu; Rui Zheng; Kui Ren; Chun Chen
Countering Backdoor Attacks in Image Recognition: A Survey and Evaluation of Mitigation Strategies. (22%)Kealan Dunnett; Reza Arablouei; Dimity Miller; Volkan Dedeoglu; Raja Jurdak
SoK: Unifying Cybersecurity and Cybersafety of Multimodal Foundation Models with an Information Theory Approach. (9%)Ruoxi Sun; Jiamin Chang; Hammond Pearce; Chaowei Xiao; Bo Li; Qi Wu; Surya Nepal; Minhui Xue
CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning. (2%)Depeng School of Computer Science and Technology, Anhui University Chen; Xiao School of Computer Science and Technology, Anhui University Liu; Jie School of Computer Science and Technology, Anhui University Cui; Hong School of Computer Science and Technology, Anhui University Zhong
2024-11-15
A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel Attacks. (98%)Benoit Coqueret; Mathieu Carbone; Olivier Sentieys; Gabriel Zaid
Edge-Only Universal Adversarial Attacks in Distributed Learning. (98%)Giulio Rossolini; Tommaso Baldi; Alessandro Biondi; Giorgio Buttazzo
Prompt-Guided Environmentally Consistent Adversarial Patch. (82%)Chaoqun Li; Huanqian Yan; Lifeng Zhou; Tairan Chen; Zhuodong Liu; Hang Su
Continual Adversarial Reinforcement Learning (CARL) of False Data Injection detection: forgetting and explainability. (81%)Pooja Aslami; Kejun Chen; Timothy M. Hansen; Malik Hassanaly
EveGuard: Defeating Vibration-based Side-Channel Eavesdropping with Audio Adversarial Perturbations. (68%)Jung-Woo Chang; Ke Sun; David Xia; Xinyu Zhang; Farinaz Koushanfar
Comparing Robustness Against Adversarial Attacks in Code Generation: LLM-Generated vs. Human-Written. (68%)Md Abdul Awal; Mrigank Rochan; Chanchal K. Roy
Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding. (11%)Huming Qiu; Guanxu Chen; Mi Zhang; Min Yang
Measuring Non-Adversarial Reproduction of Training Data in Large Language Models. (9%)Michael Aerni; Javier Rando; Edoardo Debenedetti; Nicholas Carlini; Daphne Ippolito; Florian Tramèr
Toward Robust and Accurate Adversarial Camouflage Generation against Vehicle Detectors. (1%)Jiawei Zhou; Linye Lyu; Daojing He; Yu Li
RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively. (1%)Yao Lu; Peixin Zhang; Jingyi Wang; Lei Ma; Xiaoniu Yang; Qi Xuan
2024-11-14
BEARD: Benchmarking the Adversarial Robustness for Dataset Distillation. (99%)Zheng Zhou; Wenquan Feng; Shuchang Lyu; Guangliang Cheng; Xiaowei Huang; Qi Zhao
Transferable Adversarial Attacks against ASR. (89%)Xiaoxue Gao; Zexin Li; Yiming Chen; Cong Liu; Haizhou Li
Adversarial Attacks Using Differentiable Rendering: A Survey. (83%)Matthew Hull; Chao Zhang; Zsolt Kira; Duen Horng Chau
Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey. (69%)Xuannan Liu; Xing Cui; Peipei Li; Zekun Li; Huaibo Huang; Shuhan Xia; Miaoxuan Zhang; Yueying Zou; Ran He
Your Fixed Watermark is Fragile: Towards Semantic-Aware Watermark for EaaS Copyright Protection. (11%)Zekun Fei; Biao Yi; Jianing Geng; Ruiqi He; Lihai Nie; Zheli Liu
Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology. (1%)Dhananjay Tomar; Alexander Binder; Andreas Kleppe
2024-11-13
Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness. (95%)Suhyeok Jang; Seojin Kim; Jinwoo Shin; Jongheon Jeong
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks. (81%)Zhen-Ting Liu; Shang-Tse Chen
Robust Optimal Power Flow Against Adversarial Attacks: A Tri-Level Optimization Approach. (81%)Saman Mazaheri Khamaneh; Tong Wu
The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense. (22%)Yangyang Guo; Fangkai Jiao; Liqiang Nie; Mohan Kankanhalli
LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs. (8%)Piyush Jha; Arnav Arora; Vijay Ganesh
2024-11-12
Chain Association-based Attacking and Shielding Natural Language Processing Systems. (99%)Jiacheng Huang; Long Chen
IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems. (99%)Xiaoyin Yi; Jiacheng Huang
Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models. (78%)Tiejin Chen; Kaishen Wang; Hua Wei
Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach. (67%)Jiyao Li; Mingze Ni; Yongshun Gong; Wei Liu
A Survey on Adversarial Machine Learning for Code Data: Realistic Threats, Countermeasures, and Interpretations. (64%)Yulong Yang; Haoran Fan; Chenhao Lin; Qian Li; Zhengyu Zhao; Chao Shen; Xiaohong Guan
New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook. (13%)Meng Yang; Tianqing Zhu; Chi Liu; WanLei Zhou; Shui Yu; Philip S. Yu
Adaptive Meta-Learning for Robust Deepfake Detection: A Multi-Agent Framework to Data Drift and Model Generalization. (1%)Dinesh Srivasthav P; Badri Narayan Subudhi
2024-11-11
Boosting the Targeted Transferability of Adversarial Examples via Salient Region & Weighted Feature Drop. (99%)Shanjun Xu; Linghui Li; Kaiguo Yuan; Bingyu Li
Computable Model-Independent Bounds for Adversarial Quantum Machine Learning. (69%)Bacui Li; Tansu Alpcan; Chandra Thapa; Udaya Parampalli
The Inherent Adversarial Robustness of Analog In-Memory Computing. (61%)Corey Lammie; Julian Büchel; Athanasios Vasilopoulos; Manuel Le Gallo; Abu Sebastian
Rapid Response: Mitigating LLM Jailbreaks with a Few Examples. (54%)Alwin Peng; Julian Michael; Henry Sleight; Ethan Perez; Mrinank Sharma
Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors. (1%)Anisha Pal; Julia Kruk; Mansi Phute; Manognya Bhattaram; Diyi Yang; Duen Horng Chau; Judy Hoffman
2024-11-10
Adversarial Detection with a Dynamically Stable System. (99%)Xiaowei Long; Jie Lin; Xiangyuan Yang
Deferred Backdoor Functionality Attacks on Deep Learning Models. (82%)Jeongjin Shin; Sangdon Park
SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains. (70%)Bijoy Ahmed Saiem; MD Sadik Hossain Shanto; Rakib Ahsan; Md Rafi ur Rashid
2024-11-09
Target-driven Attack for Large Language Models. (73%)Chong Zhang; Mingyu Jin; Dong Shu; Taowen Wang; Dongfang Liu; Xiaobo Jin
AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems. (33%)Zhiyu Zhu; Zhibo Jin; Hongsheng Hu; Minhui Xue; Ruoxi Sun; Seyit Camtepe; Praveen Gauravaram; Huaming Chen
2024-11-08
Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields. (41%)Yassine Abbahaddou; Sofiane Ennadir; Johannes F. Lutzeyer; Fragkiskos D. Malliaros; Michalis Vazirgiannis
Reasoning Robustness of LLMs to Adversarial Typographical Errors. (13%)Esther Gan; Yiran Zhao; Liying Cheng; Yancan Mao; Anirudh Goyal; Kenji Kawaguchi; Min-Yen Kan; Michael Shieh
Towards a Re-evaluation of Data Forging Attacks in Practice. (2%)Mohamed Suliman; Anisa Halimi; Swanand Kadhe; Nathalie Baracaldo; Douglas Leith
2024-11-07
Neural Fingerprints for Adversarial Attack Detection. (99%)Haim Fisher; Moni Shahar; Yehezkel S. Resheff
Adversarial Robustness of In-Context Learning in Transformers for Linear Regression. (98%)Usman Anwar; Oswald Johannes Von; Louis Kirsch; David Krueger; Spencer Frei
Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models. (97%)Pete Janowczyk; Linda Laurier; Ave Giulietta; Arlo Octavia; Meade Cleti
Attention Masks Help Adversarial Attacks to Bypass Safety Detectors. (97%)Yunfan Shi
Defending Deep Regression Models against Backdoor Attacks. (78%)Lingyu Du; Yupei Liu; Jinyuan Jia; Guohao Lan
Hardware and Software Platform Inference. (5%)Cheng Zhang; Hanna Foerster; Robert D. Mullins; Yiren Zhao; Ilia Shumailov
Saliency Assisted Quantization for Neural Networks. (1%)Elmira Mousa Rezabeyk; Salar Beigzad; Yasin Hamzavi; Mohsen Bagheritabar; Seyedeh Sogol Mirikhoozani
MISGUIDE: Security-Aware Attack Analytics for Smart Grid Load Frequency Control. (1%)Nur Imtiazul Haque; Prabin Mali; Mohammad Zakaria Haider; Mohammad Ashiqur Rahman; Sumit Paudyal
2024-11-06
Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging. (95%)Rui Luo; Jie Bao; Zhixin Zhou; Chuangyin Dang
Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization. (86%)Yuhao He; Jinyu Tian; Xianwei Zheng; Li Dong; Yuanman Li; Leo Yu Zhang; Jiantao Zhou
FedRISE: Rating Induced Sign Election of Gradients for Byzantine Tolerant Federated Aggregation. (41%)Joseph Geo Benjamin; Mothilal Asokan; Mohammad Yaqub; Karthik Nandakumar
MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue. (10%)Fengxiang Wang; Ranjie Duan; Peng Xiao; Xiaojun Jia; YueFeng Chen; Chongwen Wang; Jialing Tao; Hang Su; Jun Zhu; Hui Xue
Towards Secured Smart Grid 2.0: Exploring Security Threats, Protection Models, and Challenges. (4%)Lan-Huong Nguyen; Van-Linh Nguyen; Ren-Hung Hwang; Jian-Jhih Kuo; Yu-Wen Chen; Chien-Chung Huang; Ping-I Pan
Mitigating Privacy Risks in LLM Embeddings from Embedding Inversion. (1%)Tiantian Liu; Hongwei Yao; Tong Wu; Zhan Qin; Feng Lin; Kui Ren; Chun Chen
2024-11-05
Region-Guided Attack on the Segment Anything Model (SAM). (99%)Xiaoliang Liu; Furao Shen; Jian Zhao
Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training. (99%)Junhao Dong; Xinghua Qu; Z. Jane Wang; Yew-Soon Ong
Double Whammy: Stealthy Data Manipulation aided Reconstruction Attack on Graph Federated Learning. (91%)Jinyin Chen; Minying Ma; Haibin Zheng; Qi Xuan
Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras. (75%)Roberto Riaño; Gorka Abad; Stjepan Picek; Aitor Urbieta
Formal Logic-guided Robust Federated Learning against Poisoning Attacks. (68%)Dung Thuy Nguyen; Ziyan An; Taylor T. Johnson; Meiyi Ma; Kevin Leach
Oblivious Defense in ML Models: Backdoor Removal without Detection. (15%)Shafi Goldwasser; Jonathan Shafer; Neekon Vafa; Vinod Vaikuntanathan
DM4Steal: Diffusion Model For Link Stealing Attack On Graph Neural Networks. (13%)Jinyin Chen; Haonan Ma; Haibin Zheng
FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defenses. (9%)Isaac Baglin; Xiatian Zhu; Simon Hadfield
Lost in Context: The Influence of Context on Feature Attribution Methods for Object Recognition. (3%)Sayanta Adhikari; Rishav Kumar; Konda Reddy Mopuri; Rajalakshmi Pachamuthu
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset. (1%)Yingzi Ma; Jiongxiao Wang; Fei Wang; Siyuan Ma; Jiazhao Li; Xiujun Li; Furong Huang; Lichao Sun; Bo Li; Yejin Choi; Muhao Chen; Chaowei Xiao
2024-11-04
Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning. (99%)Jinyin Chen; Wenbo Mu; Luxin Zhang; Guohan Huang; Haibin Zheng; Yao Cheng
Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack. (99%)Xiaojun Jia; Sensen Gao; Qing Guo; Ke Ma; Yihao Huang; Simeng Qin; Yang Liu; Ivor Tsang Fellow; Xiaochun Cao
LiDAttack: Robust Black-box Attack on LiDAR-based Object Detection. (99%)Jinyin Chen; Danxin Liao; Sheng Xiang; Haibin Zheng
Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs. (91%)Xiaoqing Chen; Ziwei Wang; Dongrui Wu
Attacking Vision-Language Computer Agents via Pop-ups. (9%)Yanzhe Zhang; Tao Yu; Diyi Yang
FactTest: Factuality Testing in Large Language Models with Statistical Guarantees. (1%)Fan Nie; Xiaotian Hou; Shuhang Lin; James Zou; Huaxiu Yao; Linjun Zhang
Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment. (1%)Jason Vega; Junsheng Huang; Gaokai Zhang; Hangoo Kang; Minjia Zhang; Gagandeep Singh
Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognition. (1%)Idris Zakariyya; Linda Tran; Kaushik Bhargav Sivangi; Paul Henderson; Fani Deligianni
2024-11-03
Undermining Image and Text Classification Algorithms Using Adversarial Attacks. (98%)Langalibalele Lunga; Suhas Sreehari
SQL Injection Jailbreak: a structural disaster of large language models. (78%)Jiawei Zhao; Kejiang Chen; Weiming Zhang; Nenghai Yu
Rotation Perturbation Robustness in Point Cloud Analysis: A Perspective of Manifold Distillation. (2%)Xinyu Xu; Huazhen Liu; Feiming Wei; Huilin Xiong; Wenxian Yu; Tao Zhang
TabSec: A Collaborative Framework for Novel Insider Threat Detection. (1%)Zilin Huang; Xiangyan Tang; Hongyu Li; Xinyi Cao; Jieren Cheng
Learning predictable and robust neural representations by straightening image sequences. (1%)Xueyan Niu; Cristina Savin; Eero P. Simoncelli
2024-11-02
$B^4$: A Black-Box Scrubbing Attack on LLM Watermarks. (75%)Baizhou Huang; Xiao Pu; Xiaojun Wan
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks. (1%)Nathalie Maria Kirch; Severin Field; Stephen Casper
2024-11-01
Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models. (99%)Jonggyu Jang; Hyeonsu Lyu; Jungyeon Koh; Hyun Jong Yang
Defense Against Prompt Injection Attack by Leveraging Attack Techniques. (81%)Yulin Chen; Haoran Li; Zihao Zheng; Yangqiu Song; Dekai Wu; Bryan Hooi
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing. (68%)Weizhi Gao; Zhichao Hou; Han Xu; Xiaorui Liu
Attention Tracker: Detecting Prompt Injection Attacks in LLMs. (26%)Kuo-Han Hung; Ching-Yun Ko; Ambrish Rawat; I-Hsin Chung; Winston H. Hsu; Pin-Yu Chen
Emoji Attack: A Method for Misleading Judge LLMs in Safety Risk Detection. (22%)Zhipeng Wei; Yuqi Liu; N. Benjamin Erichson
Outlier-Oriented Poisoning Attack: A Grey-box Approach to Disturb Decision Boundaries by Perturbing Outliers in Multiclass Learning. (13%)Anum Paracha; Junaid Arshad; Mohamed Ben Farah; Khalid Ismail
Identify Backdoored Model in Federated Learning via Individual Unlearning. (5%)Jiahao Xu; Zikai Zhang; Rui Hu
Plentiful Jailbreaks with String Compositions. (2%)Brian R. Y. Huang
Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions. (2%)Rui Yang; Jie Wang; Guoping Wu; Bin Li
Examining Attacks on Consensus and Incentive Systems in Proof-of-Work Blockchains: A Systematic Literature Review. (1%)Dinitha Wijewardhana; Sugandima Vidanagamachchi; Nalin Arachchilage
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable. (1%)Shreyash Arya; Sukrut Rao; Moritz Böhle; Bernt Schiele
Towards Building Secure UAV Navigation with FHE-aware Knowledge Distillation. (1%)Arjun Ramesh Kaushik; Charanjit Jutla; Nalini Ratha
2024-10-31
Noise as a Double-Edged Sword: Reinforcement Learning Exploits Randomized Defenses in Neural Networks. (99%)Steve Bakos; Pooria Madani; Heidar Davoudi
Protecting Feed-Forward Networks from Adversarial Attacks Using Predictive Coding. (99%)Ehsan Ganjidoost; Jeff Orchard
Wide Two-Layer Networks can Learn from Adversarial Perturbations. (98%)Soichiro Kumano; Hiroshi Kera; Toshihiko Yamasaki
DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination. (93%)Jia Fu; Xiao Zhang; Sepideh Pashami; Fatemeh Rahimian; Anders Holst
I Can Hear You: Selective Robust Training for Deepfake Audio Detection. (86%)Zirui Zhang; Wei Hao; Aroon Sankoh; William Lin; Emanuel Mendiola-Ortiz; Junfeng Yang; Chengzhi Mao
Pseudo-Conversation Injection for LLM Goal Hijacking. (75%)Zheng Chen; Buhui Yao
ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs. (41%)Yuchen Yang; Shubham Ugare; Yifan Zhao; Gagandeep Singh; Sasa Misailovic
Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving. (5%)Ce Michigan State University Zhou; Qiben Michigan State University Yan; Daniel Michigan State University Kent; Guangjing University of South Florida Wang; Weikang Michigan State University Ding; Ziqi Peking University Zhang; Hayder Michigan State University Radha
Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey. (2%)Chiyu Zhang; Xiaogang Xu; Jiafei Wu; Zhe Liu; Lu Zhou
2024-10-30
FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training. (99%)Tejaswini Medi; Steffen Jung; Margret Keuper
Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System. (99%)Julian Collado; Kevin Stangl
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense. (99%)Mingkun Zhang; Keping Bi; Wei Chen; Quanrun Chen; Jiafeng Guo; Xueqi Cheng
One Prompt to Verify Your Models: Black-Box Text-to-Image Models Verification via Non-Transferable Adversarial Attacks. (98%)Ji Guo; Wenbo Jiang; Rui Zhang; Guoming Lu; Hongwei Li
Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector. (87%)Youcheng Huang; Fengbin Zhu; Jingkun Tang; Pan Zhou; Wenqiang Lei; Jiancheng Lv; Tat-Seng Chua
HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models. (82%)Yucheng Zhang; Qinfeng Li; Tianyu Du; Xuhong Zhang; Xinkui Zhao; Zhengwen Feng; Jianwei Yin
Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation. (67%)Kaike Zhang; Qi Cao; Yunfan Wu; Fei Sun; Huawei Shen; Xueqi Cheng
Teaching a Language Model to Distinguish Between Similar Details using a Small Adversarial Training Set. (64%)Chris Achard
Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosion. (62%)Ji Guo; Hongwei Li; Wenbo Jiang; Guoming Lu
Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images. (2%)Qi Song; Ziyuan Luo; Ka Chun Cheung; Simon See; Renjie Wan
Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols. (1%)Atharv Deshmukh
ProTransformer: Robustify Transformers via Plug-and-Play Paradigm. (1%)Zhichao Hou; Weizhi Gao; Yuchen Shen; Feiyi Wang; Xiaorui Liu
Attribute-to-Delete: Machine Unlearning via Datamodel Matching. (1%)Kristian Georgiev; Roy Rinberg; Sung Min Park; Shivam Garg; Andrew Ilyas; Aleksander Madry; Seth Neel
Stealing User Prompts from Mixture of Experts. (1%)Itay Yona; Ilia Shumailov; Jamie Hayes; Nicholas Carlini
InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models. (1%)Hao Li; Xiaogeng Liu; Chaowei Xiao
2024-10-29
On the Robustness of Adversarial Training Against Uncertainty Attacks. (99%)Emanuele Ledda; Giovanni Scodeller; Daniele Angioni; Giorgio Piras; Antonio Emanuele Cinà; Giorgio Fumera; Battista Biggio; Fabio Roli
CausAdv: A Causal-based Framework for Detecting Adversarial Examples. (99%)Hichem Debbi
Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models. (98%)Lu Yu; Haiyang Zhang; Changsheng Xu
IDEATOR: Jailbreaking Large Vision-Language Models Using Themselves. (83%)Ruofan Wang; Bo Wang; Xiaosen Wang; Xingjun Ma; Yu-Gang Jiang
Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers. (82%)Lam Nguyen Tung; Steven Cho; Xiaoning Du; Neelofar Neelofar; Valerio Terragni; Stefano Ruberto; Aldeida Aleti
Longitudinal Mammogram Exam-based Breast Cancer Diagnosis Models: Vulnerability to Adversarial Attacks. (81%)Zhengbo Zhou; Degan Hao; Dooman Arefan; Margarita Zuley; Jules Sumkin; Shandong Wu
AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts. (78%)Vishal Kumar; Zeyi Liao; Jaylen Jones; Huan Sun
Embedding-based classifiers can detect prompt injection attacks. (64%)Md. Ahsan Ayub; Subhabrata Majumdar
Enhancing Adversarial Attacks through Chain of Thought. (54%)Jingbo Su
Power side-channel leakage localization through adversarial training of deep neural networks. (11%)Jimmy Gammell; Anand Raghunathan; Kaushik Roy
Enhancing Safety and Robustness of Vision-Based Controllers via Reachability Analysis. (1%)Kaustav Chakraborty; Aryaman Gupta; Somil Bansal
DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models. (1%)Chengke Zou; Xingang Guo; Rui Yang; Junyu Zhang; Bin Hu; Huan Zhang
2024-10-28
Evaluating the Robustness of LiDAR Point Cloud Tracking Against Adversarial Attack. (99%)Shengjing Tian; Yinan Han; Xiantong Zhao; Bin Liu; Xiuping Liu
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models. (96%)Yaopei Zeng; Yuanpu Cao; Bochuan Cao; Yurui Chang; Jinghui Chen; Lu Lin
BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks. (93%)Yunhan Zhao; Xiang Zheng; Lin Luo; Yige Li; Xingjun Ma; Yu-Gang Jiang
FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks. (91%)Jiongxiao Wang; Fangzhou Wu; Wendi Li; Jinsheng Pan; Edward Suh; Z. Morley Mao; Muhao Chen; Chaowei Xiao
TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors. (88%)Adonisz Dimitriu; Tamás Michaletzky; Viktor Remeli
Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models. (83%)Piotr Przybyła
Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks. (80%)Dario Pasquini; Evgenios M. Kornaropoulos; Giuseppe Ateniese
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring. (50%)Honglin Mu; Han He; Yuxin Zhou; Yunlong Feng; Yang Xu; Libo Qin; Xiaoming Shi; Zeming Liu; Xudong Han; Qi Shi; Qingfu Zhu; Wanxiang Che
Mitigating Unauthorized Speech Synthesis for Voice Protection. (9%)Zhisheng Zhang; Qianyi Yang; Derui Wang; Pengyang Huang; Yuxin Cao; Kai Ye; Jie Hao
Palisade -- Prompt Injection Detection Framework. (1%)Sahasra Kokkula; Somanathan R; Nandavardhan R; Aashishkumar; G Divya
2024-10-27
Integrating uncertainty quantification into randomized smoothing based robustness guarantees. (98%)Sina Däubener; Kira Maag; David Krueger; Asja Fischer
LLM Robustness Against Misinformation in Biomedical Question Answering. (80%)Alexander Bondarenko; Adrian Viehweger
Fine-tuned Large Language Models (LLMs): Improved Prompt Injection Attacks Detection. (1%)Md Abdur Rahman; Fan Wu; Alfredo Cuzzocrea; Sheikh Iqbal Ahamed
2024-10-26
Adversarial Attacks Against Double RIS-Assisted MIMO Systems-based Autoencoder in Finite-Scattering Environments. (99%)Bui Duc Son; Ngo Nam Khanh; Chien Trinh Van; Dong In Kim
Transferable Adversarial Attacks on SAM and Its Downstream Models. (99%)Song Xia; Wenhan Yang; Yi Yu; Xun Lin; Henghui Ding; Lingyu Duan; Xudong Jiang
Generative Adversarial Patches for Physical Attacks on Cross-Modal Pedestrian Re-Identification. (98%)Yue Su; Hao Li; Maoguo Gong
CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification. (76%)Fangwen Mu; Junjie Wang; Zhuohao Yu; Lin Shi; Song Wang; Mingyang Li; Qing Wang
Robust Model Evaluation over Large-scale Federated Networks. (2%)Amir Najafi; Samin Mahdizadeh Sani; Farzan Farnia
2024-10-25
GPT-4o System Card. (76%)Tony OpenAI; Tony :; Aaron Tony Hurst; Adam Tony Lerer; Adam P. Tony Goucher; Adam Tony Perelman; Aditya Tony Ramesh; Aidan Tony Clark; AJ Tony Ostrow; Akila Tony Welihinda; Alan Tony Hayes; Alec Tony Radford; Aleksander Tony Mądry; Alex Tony Baker-Whitcomb; Alex Tony Beutel; Alex Tony Borzunov; Alex Tony Carney; Alex Tony Chow; Alex Tony Kirillov; Alex Tony Nichol; Alex Tony Paino; Alex Tony Renzin; Alex Tachard Tony Passos; Alexander Tony Kirillov; Alexi Tony Christakis; Alexis Tony Conneau; Ali Tony Kamali; Allan Tony Jabri; Allison Tony Moyer; Allison Tony Tam; Amadou Tony Crookes; Amin Tony Tootoochian; Amin Tony Tootoonchian; Ananya Tony Kumar; Andrea Tony Vallone; Andrej Tony Karpathy; Andrew Tony Braunstein; Andrew Tony Cann; Andrew Tony Codispoti; Andrew Tony Galu; Andrew Tony Kondrich; Andrew Tony Tulloch; Andrey Tony Mishchenko; Angela Tony Baek; Angela Tony Jiang; Antoine Tony Pelisse; Antonia Tony Woodford; Anuj Tony Gosalia; Arka Tony Dhar; Ashley Tony Pantuliano; Avi Tony Nayak; Avital Tony Oliver; Barret Tony Zoph; Behrooz Tony Ghorbani; Ben Tony Leimberger; Ben Tony Rossen; Ben Tony Sokolowsky; Ben Tony Wang; Benjamin Tony Zweig; Beth Tony Hoover; Blake Tony Samic; Bob Tony McGrew; Bobby Tony Spero; Bogo Tony Giertler; Bowen Tony Cheng; Brad Tony Lightcap; Brandon Tony Walkin; Brendan Tony Quinn; Brian Tony Guarraci; Brian Tony Hsu; Bright Tony Kellogg; Brydon Tony Eastman; Camillo Tony Lugaresi; Carroll Tony Wainwright; Cary Tony Bassin; Cary Tony Hudson; Casey Tony Chu; Chad Tony Nelson; Chak Tony Li; Chan Jun Tony Shern; Channing Tony Conger; Charlotte Tony Barette; Chelsea Tony Voss; Chen Tony Ding; Cheng Tony Lu; Chong Tony Zhang; Chris Tony Beaumont; Chris Tony Hallacy; Chris Tony Koch; Christian Tony Gibson; Christina Tony Kim; Christine Tony Choi; Christine Tony McLeavey; Christopher Tony Hesse; Claudia Tony Fischer; Clemens Tony Winter; Coley Tony Czarnecki; Colin Tony Jarvis; Colin Tony Wei; Constantin Tony Koumouzelis; Dane Tony Sherburn; Daniel Tony Kappler; Daniel Tony Levin; Daniel Tony Levy; David Tony Carr; David Tony Farhi; David Tony Mely; David Tony Robinson; David Tony Sasaki; Denny Tony Jin; Dev Tony Valladares; Dimitris Tony Tsipras; Doug Tony Li; Duc Phong Tony Nguyen; Duncan Tony Findlay; Edede Tony Oiwoh; Edmund Tony Wong; Ehsan Tony Asdar; Elizabeth Tony Proehl; Elizabeth Tony Yang; Eric Tony Antonow; Eric Tony Kramer; Eric Tony Peterson; Eric Tony Sigler; Eric Tony Wallace; Eugene Tony Brevdo; Evan Tony Mays; Farzad Tony Khorasani; Felipe Petroski Tony Such; Filippo Tony Raso; Francis Tony Zhang; Lohmann Fred Tony von; Freddie Tony Sulit; Gabriel Tony Goh; Gene Tony Oden; Geoff Tony Salmon; Giulio Tony Starace; Greg Tony Brockman; Hadi Tony Salman; Haiming Tony Bao; Haitang Tony Hu; Hannah Tony Wong; Haoyu Tony Wang; Heather Tony Schmidt; Heather Tony Whitney; Heewoo Tony Jun; Hendrik Tony Kirchner; Henrique Ponde de Oliveira Tony Pinto; Hongyu Tony Ren; Huiwen Tony Chang; Hyung Won Tony Chung; Ian Tony Kivlichan; Ian Tony O'Connell; Ian Tony O'Connell; Ian Tony Osband; Ian Tony Silber; Ian Tony Sohl; Ibrahim Tony Okuyucu; Ikai Tony Lan; Ilya Tony Kostrikov; Ilya Tony Sutskever; Ingmar Tony Kanitscheider; Ishaan Tony Gulrajani; Jacob Tony Coxon; Jacob Tony Menick; Jakub Tony Pachocki; James Tony Aung; James Tony Betker; James Tony Crooks; James Tony Lennon; Jamie Tony Kiros; Jan Tony Leike; Jane Tony Park; Jason Tony Kwon; Jason Tony Phang; Jason Tony Teplitz; Jason Tony Wei; Jason Tony Wolfe; Jay Tony Chen; Jeff Tony Harris; Jenia Tony Varavva; Jessica Gan Tony Lee; Jessica Tony Shieh; Ji Tony Lin; Jiahui Tony Yu; Jiayi Tony Weng; Jie Tony Tang; Jieqi Tony Yu; Joanne Tony Jang; Joaquin Quinonero Tony Candela; Joe Tony Beutler; Joe Tony Landers; Joel Tony Parish; Johannes Tony Heidecke; John Tony Schulman; Jonathan Tony Lachman; Jonathan Tony McKay; Jonathan Tony Uesato; Jonathan Tony Ward; Jong Wook Tony Kim; Joost Tony Huizinga; Jordan Tony Sitkin; Jos Tony Kraaijeveld; Josh Tony Gross; Josh Tony Kaplan; Josh Tony Snyder; Joshua Tony Achiam; Joy Tony Jiao; Joyce Tony Lee; Juntang Tony Zhuang; Justyn Tony Harriman; Kai Tony Fricke; Kai Tony Hayashi; Karan Tony Singhal; Katy Tony Shi; Kavin Tony Karthik; Kayla Tony Wood; Kendra Tony Rimbach; Kenny Tony Hsu; Kenny Tony Nguyen; Keren Tony Gu-Lemberg; Kevin Tony Button; Kevin Tony Liu; Kiel Tony Howe; Krithika Tony Muthukumar; Kyle Tony Luther; Lama Tony Ahmad; Larry Tony Kai; Lauren Tony Itow; Lauren Tony Workman; Leher Tony Pathak; Leo Tony Chen; Li Tony Jing; Lia Tony Guy; Liam Tony Fedus; Liang Tony Zhou; Lien Tony Mamitsuka; Lilian Tony Weng; Lindsay Tony McCallum; Lindsey Tony Held; Long Tony Ouyang; Louis Tony Feuvrier; Lu Tony Zhang; Lukas Tony Kondraciuk; Lukasz Tony Kaiser; Luke Tony Hewitt; Luke Tony Metz; Lyric Tony Doshi; Mada Tony Aflak; Maddie Tony Simens; Madelaine Tony Boyd; Madeleine Tony Thompson; Marat Tony Dukhan; Mark Tony Chen; Mark Tony Gray; Mark Tony Hudnall; Marvin Tony Zhang; Marwan Tony Aljubeh; Mateusz Tony Litwin; Matthew Tony Zeng; Max Tony Johnson; Maya Tony Shetty; Mayank Tony Gupta; Meghan Tony Shah; Mehmet Tony Yatbaz; Meng Jia Tony Yang; Mengchao Tony Zhong; Mia Tony Glaese; Mianna Tony Chen; Michael Tony Janner; Michael Tony Lampe; Michael Tony Petrov; Michael Tony Wu; Michele Tony Wang; Michelle Tony Fradin; Michelle Tony Pokrass; Miguel Tony Castro; Castro Miguel Oom Temudo Tony de; Mikhail Tony Pavlov; Miles Tony Brundage; Miles Tony Wang; Minal Tony Khan; Mira Tony Murati; Mo Tony Bavarian; Molly Tony Lin; Murat Tony Yesildal; Nacho Tony Soto; Natalia Tony Gimelshein; Natalie Tony Cone; Natalie Tony Staudacher; Natalie Tony Summers; Natan Tony LaFontaine; Neil Tony Chowdhury; Nick Tony Ryder; Nick Tony Stathas; Nick Tony Turley; Nik Tony Tezak; Niko Tony Felix; Nithanth Tony Kudige; Nitish Tony Keskar; Noah Tony Deutsch; Noel Tony Bundick; Nora Tony Puckett; Ofir Tony Nachum; Ola Tony Okelola; Oleg Tony Boiko; Oleg Tony Murk; Oliver Tony Jaffe; Olivia Tony Watkins; Olivier Tony Godement; Owen Tony Campbell-Moore; Patrick Tony Chao; Paul Tony McMillan; Pavel Tony Belov; Peng Tony Su; Peter Tony Bak; Peter Tony Bakkum; Peter Tony Deng; Peter Tony Dolan; Peter Tony Hoeschele; Peter Tony Welinder; Phil Tony Tillet; Philip Tony Pronin; Philippe Tony Tillet; Prafulla Tony Dhariwal; Qiming Tony Yuan; Rachel Tony Dias; Rachel Tony Lim; Rahul Tony Arora; Rajan Tony Troll; Randall Tony Lin; Rapha Gontijo Tony Lopes; Raul Tony Puri; Reah Tony Miyara; Reimar Tony Leike; Renaud Tony Gaubert; Reza Tony Zamani; Ricky Tony Wang; Rob Tony Donnelly; Rob Tony Honsby; Rocky Tony Smith; Rohan Tony Sahai; Rohit Tony Ramchandani; Romain Tony Huet; Rory Tony Carmichael; Rowan Tony Zellers; Roy Tony Chen; Ruby Tony Chen; Ruslan Tony Nigmatullin; Ryan Tony Cheu; Saachi Tony Jain; Sam Tony Altman; Sam Tony Schoenholz; Sam Tony Toizer; Samuel Tony Miserendino; Sandhini Tony Agarwal; Sara Tony Culver; Scott Tony Ethersmith; Scott Tony Gray; Sean Tony Grove; Sean Tony Metzger; Shamez Tony Hermani; Shantanu Tony Jain; Shengjia Tony Zhao; Sherwin Tony Wu; Shino Tony Jomoto; Shirong Tony Wu; Tony Shuaiqi; Xia; Sonia Phene; Spencer Papay; Srinivas Narayanan; Steve Coffey; Steve Lee; Stewart Hall; Suchir Balaji; Tal Broda; Tal Stramer; Tao Xu; Tarun Gogineni; Taya Christianson; Ted Sanders; Tejal Patwardhan; Thomas Cunninghman; Thomas Degry; Thomas Dimson; Thomas Raoux; Thomas Shadwell; Tianhao Zheng; Todd Underwood; Todor Markov; Toki Sherbakov; Tom Rubin; Tom Stasi; Tomer Kaftan; Tristan Heywood; Troy Peterson; Tyce Walters; Tyna Eloundou; Valerie Qi; Veit Moeller; Vinnie Monaco; Vishal Kuo; Vlad Fomenko; Wayne Chang; Weiyi Zheng; Wenda Zhou; Wesam Manassra; Will Sheu; Wojciech Zaremba; Yash Patil; Yilei Qian; Yongjik Kim; Youlong Cheng; Yu Zhang; Yuchen He; Yuchen Zhang; Yujia Jin; Yunxing Dai; Yury Malkov
RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction. (64%)Tanqiu Jiang; Zian Wang; Jiacheng Liang; Changjiang Li; Yuhui Wang; Ting Wang
Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions. (62%)Poojitha Thota; Shirin Nilizadeh
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models. (56%)Yige Li; Hanxun Huang; Jiaming Zhang; Xingjun Ma; Yu-Gang Jiang
Towards Robust Algorithms for Surgical Phase Recognition via Digital Twin-based Scene Representation. (2%)Hao Ding; Yuqian Zhang; Hongchao Shu; Xu Lian; Ji Woong Kim; Axel Krieger; Mathias Unberath
2024-10-24
GADT: Enhancing Transferable Adversarial Attacks through Gradient-guided Adversarial Data Transformation. (99%)Yating Ma; Xiaogang Xu; Liming Fang; Zhe Liu
Adversarial Attacks on Large Language Models Using Regularized Relaxation. (98%)Samuel Jacob Chacko; Sajib Biswas; Chashi Mahiul Islam; Fatema Tabassum Liza; Xiuwen Liu
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities. (88%)Chung-En Sun; Xiaodong Liu; Weiwei Yang; Tsui-Wei Weng; Hao Cheng; Aidan San; Michel Galley; Jianfeng Gao
Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors. (68%)Tianchun Wang; Yuanzhou Chen; Zichuan Liu; Zhanwen Chen; Haifeng Chen; Xiang Zhang; Wei Cheng
Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustness. (33%)David Khachaturov; Robert Mullins
Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances. (11%)Shilin Lu; Zihan Zhou; Jiayou Lu; Yuanzhi Zhu; Adams Wai-Kin Kong
2024-10-23
Advancing NLP Security by Leveraging LLMs as Adversarial Engines. (98%)Sudarshan Srinivasan; Maria Mahbub; Amir Sadovnik
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing. (93%)Dongliang Guo; Mengxuan Hu; Zihan Guan; Junfeng Guo; Thomas Hartvigsen; Sheng Li
Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detection. (70%)Jakob Shack; Katarina Petrovic; Olga Saukh
Slot: Provenance-Driven APT Detection through Graph Reinforcement Learning. (16%)Wei Qiao; Yebo Feng; Teng Li; Zijian Zhang; Zhengzi Xu; Zhuo Ma; Yulong Shen; JianFeng Ma; Yang Liu
Guide for Defense (G4D): Dynamic Guidance for Robust and Balanced Defense in Large Language Models. (9%)He Cao; Weidi Luo; Yu Wang; Zijing Liu; Bing Feng; Yuan Yao; Yu Li
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks. (2%)Samuele Poppi; Zheng-Xin Yong; Yifei He; Bobbie Chern; Han Zhao; Aobo Yang; Jianfeng Chi
Countering Autonomous Cyber Threats. (2%)Kade M. Heckel; Adrian Weller
Is Smoothness the Key to Robustness? A Comparison of Attention and Convolution Models Using a Novel Metric. (1%)Baiyuan Chen
2024-10-22
Detecting Adversarial Examples. (99%)Furkan Mumcu; Yasin Yilmaz
Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Cost. (98%)Cheng-Han Yeh; Kuanchun Yu; Chun-Shien Lu
AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents. (97%)Chejian Xu; Mintong Kang; Jiawei Zhang; Zeyi Liao; Lingbo Mo; Mengqi Yuan; Huan Sun; Bo Li
Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks. (67%)Tao Li; Henger Li; Yunian Pan; Tianyi Xu; Zizhan Zheng; Quanyan Zhu
Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense. (41%)Aditya Vikram Singh; Ethan Rathbun; Emma Graham; Lisa Oakley; Simona Boboila; Alina Oprea; Peter Chin
On the Vulnerability of Text Sanitization. (8%)Meng Tong; Kejiang Chen; Xiaojian Yuang; Jiayang Liu; Weiming Zhang; Nenghai Yu; Jie Zhang
Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods. (5%)Tsachi Blau; Moshe Kimhi; Yonatan Belinkov; Alexander Bronstein; Chaim Baskin
Evaluating the Effectiveness of Attack-Agnostic Features for Morphing Attack Detection. (4%)Laurent Colbois; Sébastien Marcel
BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers. (2%)Jiaqi Xue; Qian Lou; Mengxin Zheng
Invisible Manipulation Deep Reinforcement Learning Enhanced Stealthy Attacks on Battery Energy Management Systems. (1%)Qi Xiao; Lidong Song; Jongha Woo; Rongxing Hu; Bei Xu; Ning Lu
A Hybrid Simulation of DNN-based Gray Box Models. (1%)Aayushya Agarwal; Yihan Ruan; Larry Pileggi
2024-10-21
Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples. (99%)Kirill Lukyanov; Andrew Perminov; Denis Turdakov; Mikhail Pautov
Conflict-Aware Adversarial Training. (70%)Zhiyu Xue; Haohan Wang; Yao Qin; Ramtin Pedarsani
Robust Feature Learning for Multi-Index Models in High Dimensions. (68%)Alireza Mousavi-Hosseini; Adel Javanmard; Murat A. Erdogdu
Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splitting. (16%)Bao Q. Tran; Viet Nguyen; Anh Tran; Toan Tran
Metric as Transform: Exploring beyond Affine Transform for Interpretable Neural Network. (13%)Suman Sapkota
A Realistic Threat Model for Large Language Model Jailbreaks. (11%)Valentyn Boreiko; Alexander Panfilov; Vaclav Voracek; Matthias Hein; Jonas Geiping
Vulnerabilities in Machine Learning-Based Voice Disorder Detection Systems. (11%)Gianpaolo Perelli; Andrea Panzino; Roberto Casula; Marco Micheletto; Giulia Orrù; Gian Luca Marcialis
On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds. (5%)Matteo Vilucchio; Nikolaos Tsilivis; Bruno Loureiro; Julia Kempe
Boosting Jailbreak Transferability for Large Language Models. (1%)Hanqing Liu; Lifeng Zhou; Huanqian Yan
Extracting Spatiotemporal Data from Gradients with Large Language Models. (1%)Lele Zheng; Yang Cao; Renhe Jiang; Kenjiro Taura; Yulong Shen; Sheng Li; Masatoshi Yoshikawa
2024-10-20
PEAS: A Strategy for Crafting Transferable Adversarial Examples. (99%)Bar Avraham; Yisroel Mirsky
Efficient Model Extraction via Boundary Sampling. (96%)Maor Biton Dor; Yisroel Mirsky
The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks. (76%)Daniel Ayzenshteyn; Roy Weiss; Yisroel Mirsky
Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models. (45%)Xiao Li; Zhuhong Li; Qiongxiu Li; Bingze Lee; Jinghao Cui; Xiaolin Hu
Bayesian Concept Bottleneck Models with LLM Priors. (1%)Jean Feng; Avni Kothari; Luke Zier; Chandan Singh; Yan Shuo Tan
2024-10-19
Adversarial Training: A Survey. (97%)Mengnan Zhao; Lihe Zhang; Jingwen Ye; Huchuan Lu; Baocai Yin; Xinchao Wang
Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models. (92%)Seong-Il Park; Jay-Yoon Lee
Beyond Pruning Criteria: The Dominant Role of Fine-Tuning and Adaptive Ratios in Neural Network Robustness. (76%)Lincen Bai; Hedi Tabia; Raúl Santos-Rodríguez
Jailbreaking and Mitigation of Vulnerabilities in Large Language Models. (50%)Benji Peng; Ziqian Bi; Qian Niu; Ming Liu; Pohsun Feng; Tianyang Wang; Lawrence K. Q. Yan; Yizhu Wen; Yichao Zhang; Caitlyn Heqi Yin
SLIC: Secure Learned Image Codec through Compressed Domain Watermarking to Defend Image Manipulation. (11%)Chen-Hsiu Huang; Ja-Ling Wu
DynaMO: Protecting Mobile DL Models through Coupling Obfuscated DL Operators. (2%)Mingyi Zhou; Xiang Gao; Xiao Chen; Chunyang Chen; John Grundy; Li Li
2024-10-18
A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models. (99%)Yuhan Liang; Yijun Li; Yumeng Niu; Qianhe Shen; Hangyu Liu
Class-RAG: Content Moderation with Retrieval Augmented Generation. (75%)Jianfa Chen; Emily Shen; Trupti Bavalatti; Xiaowen Lin; Yongkai Wang; Shuming Hu; Harihar Subramanyam; Ksheeraj Sai Vepuri; Ming Jiang; Ji Qi; Li Chen; Nan Jiang; Ankit Jain
Attack as Defense: Run-time Backdoor Implantation for Image Content Protection. (61%)Haichuan Zhang; Meiyu Lin; Zhaoyi Liu; Renyuan Li; Zhiyuan Cheng; Carl Yang; Mingjie Tang
Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs. (13%)Rui Pu; Chaozhuo Li; Rui Ha; Zejian Chen; Litian Zhang; Zheng Liu; Lirong Qiu; Xi Zhang
Stochastic Gradient Descent Jittering for Inverse Problems: Alleviating the Accuracy-Robustness Tradeoff. (10%)Peimeng Guan; Mark A. Davenport
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation. (5%)Shuai Zhao; Xiaobao Wu; Cong-Duy Nguyen; Meihuizi Jia; Yichao Feng; Luu Anh Tuan
Real-time Fake News from Adversarial Feedback. (3%)Sanxing Chen; Yukun Huang; Bhuwan Dhingra
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step. (1%)Mingyuan Zhou; Huangjie Zheng; Yi Gu; Zhendong Wang; Hai Huang
2024-10-17
MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks. (99%)Xinxin Liu; Zhongliang Guo; Siyuan Huang; Chun Pong Lau
DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks. (95%)Hao Sui; Bing Chen; Jiale Zhang; Chengcheng Zhu; Di Wu; Qinghua Lu; Guodong Long
Adversarial Inception for Bounded Backdoor Poisoning in Deep Reinforcement Learning. (67%)Ethan Rathbun; Christopher Amato; Alina Oprea
SPIN: Self-Supervised Prompt INjection. (67%)Leon Zhou; Junfeng Yang; Chengzhi Mao
Jailbreaking LLM-Controlled Robots. (56%)Alexander Robey; Zachary Ravichandran; Vijay Kumar; Hamed Hassani; George J. Pappas
Persistent Pre-Training Poisoning of LLMs. (33%)Yiming Zhang; Javier Rando; Ivan Evtimov; Jianfeng Chi; Eric Michael Smith; Nicholas Carlini; Florian Tramèr; Daphne Ippolito
Trojan Prompt Attacks on Graph Neural Networks. (4%)Minhua Lin; Zhiwei Zhang; Enyan Dai; Zongyu Wu; Yilong Wang; Xiang Zhang; Suhang Wang
Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems. (2%)Isack Lee; Haebin Seong
2024-10-16
Golyadkin's Torment: Doppelg\"angers and Adversarial Vulnerability. (99%)George I. Kamberov
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain. (99%)Fengpeng Li; Kemou Li; Haiwei Wu; Jinyu Tian; Jiantao Zhou
Boosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with Momentum. (99%)Nashrah Haque; Xiang Li; Zhehui Chen; Yanzhao Wu; Lei Yu; Arun Iyengar; Wenqi Wei
New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes. (98%)Yanyun Wang; Li Liu; Zi Liang; Qingqing Ye; Haibo Hu
Perseus: Leveraging Common Data Patterns with Curriculum Learning for More Robust Graph Neural Networks. (92%)Kaiwen Xia; Huijun Wu; Duanyu Li; Min Xie; Ruibo Wang; Wenzhe Zhang
Low-Rank Adversarial PGD Attack. (84%)Dayana Savostianova; Emanuele Zangrando; Francesco Tudisco
Data Defenses Against Large Language Models. (76%)William Agnew; Harry H. Jiang; Cella Sum; Maarten Sap; Sauvik Das
Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images. (61%)Arka Daw; Megan Hong-Thanh Chung; Maria Mahbub; Amir Sadovnik
NSmark: Null Space Based Black-box Watermarking Defense Framework for Pre-trained Language Models. (16%)Haodong Zhao; Jinming Hu; Peixuan Li; Fangqi Li; Jinrui Sha; Peixuan Chen; Zhuosheng Zhang; Gongshen Liu
Reconstruction of Differentially Private Text Sanitization via Large Language Models. (4%)Shuchao Pang; Zhigang Lu; Haichen Wang; Peng Fu; Yongbin Zhou; Minhui Xue; Bo Li
Unitary Multi-Margin BERT for Robust Natural Language Processing. (4%)Hao-Yuan Chang; Kang L. Wang
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace. (2%)Jinluan Yang; Anke Tang; Didi Zhu; Zhengyu Chen; Li Shen; Fei Wu
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning. (2%)Evelyn Ma; Chao Pan; Rasoul Etesami; Han Zhao; Olgica Milenkovic
Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors. (2%)Linwei Tao; Haolan Guo; Minjing Dong; Chang Xu
Efficient Optimization Algorithms for Linear Adversarial Training. (1%)Antônio H. RIbeiro; Thomas B. Schön; Dave Zahariah; Francis Bach
PromptExp: Multi-granularity Prompt Explanation of Large Language Models. (1%)Ximing Dong; Shaowei Wang; Dayi Lin; Gopi Krishnan Rajbahadur; Boquan Zhou; Shichao Liu; Ahmed E. Hassan
Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations. (1%)Lu Pang; Tao Sun; Weimin Lyu; Haibin Ling; Chao Chen
2024-10-15
Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks. (99%)Kevin Eykholt; Farhan Ahmed; Pratik Vaishnavi; Amir Rahmati
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models. (98%)Fan Yang; Yihao Huang; Kailong Wang; Ling Shi; Geguang Pu; Yang Liu; Haoyu Wang
Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation. (83%)Qizhang Li; Xiaochen Yang; Wangmeng Zuo; Yiwen Guo
BeniFul: Backdoor Defense via Middle Feature Analysis for Deep Neural Networks. (82%)Xinfu Li; Junying Zhang; Xindi Ma
Cognitive Overload Attack:Prompt Injection for Long Context. (62%)Bibek Upadhayay; Vahid Behzadan; Amin Karbasi
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment. (31%)Pankayaraj Pathmanathan; Udari Madhushani Sehwag; Michael-Andrei Panaitescu-Liess; Furong Huang
Backdoor Attack on Vertical Federated Graph Neural Network Learning. (10%)Jirui Yang; Peng Chen; Zhihui Lu; Ruijun Deng; Qiang Duan; Jianping Zeng
DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks. (10%)Zohreh Aghababaeyan; Manel Abdellatif; Lionel Briand; Ramesh S
Multi-round jailbreak attack on large language models. (4%)Yihua Zhou; Xiaochuan Shi
Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture. (3%)Sajad Movahedi; Antonio Orvieto; Seyed-Mohsen Moosavi-Dezfooli
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks. (2%)Guibin Zhang; Yanwei Yue; Xiangguo Sun; Guancheng Wan; Miao Yu; Junfeng Fang; Kun Wang; Dawei Cheng
2024-10-14
Denial-of-Service Poisoning Attacks against Large Language Models. (92%)Kuofeng Gao; Tianyu Pang; Chao Du; Yong Yang; Shu-Tao Xia; Min Lin
Towards Calibrated Losses for Adversarial Robust Reject Option Classification. (86%)Vrund Shah; Tejas Chaudhari; Naresh Manwani
Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings. (86%)Hossein Mirzaei; Mackenzie W. Mathis
Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning. (81%)Hassan Ali; Surya Nepal; Salil S. Kanhere; Sanjay Jha
Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks. (68%)Binghui Li; Zhixuan Pan; Kaifeng Lyu; Jian Li
ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection. (67%)Martin Aubard; László Antal; Ana Madureira; Luis F. Teixeira; Erika Ábrahám
Generalized Adversarial Code-Suggestions: Exploiting Contexts of LLM-based Code-Completion. (15%)Karl Rubel; Maximilian Noppel; Christian Wressnegger
Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach. (13%)Rory Young; Nicolas Pugeault
How to Backdoor Consistency Models? (12%)Chengen Wang; Murat Kantarcioglu
The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels. (2%)Yonatan Slutzky; Yotam Alexander; Noam Razin; Nadav Cohen
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance. (1%)Sachin Goyal; Christina Baek; J. Zico Kolter; Aditi Raghunathan
On Calibration of LLM-based Guard Models for Reliable Content Moderation. (1%)Hongfu Liu; Hengguan Huang; Hao Wang; Xiangming Gu; Ye Wang
Regularized Robustly Reliable Learners and Instance Targeted Attacks. (1%)Avrim Blum; Donya Saless
Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models. (1%)Zhongye Liu; Hongbin Liu; Yuepeng Hu; Zedian Shao; Neil Zhenqiang Gong
2024-10-13
S$^4$ST: A Strong, Self-transferable, faSt, and Simple Scale Transformation for Transferable Targeted Attack. (99%)Yongxiang Liu; Bowen Peng; Li Liu; Xiang Li
Understanding Robustness of Parameter-Efficient Tuning for Image Classification. (98%)Jiacheng Ruan; Xian Gao; Suncheng Xiang; Mingye Xie; Ting Liu; Yuzhuo Fu
Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors. (75%)Tao Lin; Lijia Yu; Gaojie Jin; Renjue Li; Peng Wu; Lijun Zhang
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense. (67%)Rui Min; Zeyu Qin; Nevin L. Zhang; Li Shen; Minhao Cheng
BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models. (13%)Xinyuan Wang; Victor Shea-Jay Huang; Renmiao Chen; Hao Wang; Chengwei Pan; Lei Sha; Minlie Huang
Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation. (1%)Guozhi Liu; Weiwei Lin; Tiansheng Huang; Ruichao Mo; Qi Mu; Li Shen
2024-10-12
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy. (91%)Yangsibo Huang; Daogao Liu; Lynn Chua; Badih Ghazi; Pritish Kamath; Ravi Kumar; Pasin Manurangsi; Milad Nasr; Amer Sinha; Chiyuan Zhang
Robust 3D Point Clouds Classification based on Declarative Defenders. (2%)Kaidong Li; Tianxiao Zhang; Cuncong Zhong; Ziming Zhang; Guanghui Wang
2024-10-11
On the Adversarial Transferability of Generalized "Skip Connections". (99%)Yisen Wang; Yichuan Mo; Dongxian Wu; Mingjie Li; Xingjun Ma; Zhouchen Lin
Natural Language Induced Adversarial Images. (99%)Xiaopei Zhu; Peiyang Xu; Guanning Zeng; Yingpeng Dong; Xiaolin Hu
Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks. (70%)Isha Gupta; Hidde Lycklama; Emanuel Opel; Evan Rose; Anwar Hithnawi
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents. (69%)Maksym Andriushchenko; Alexandra Souly; Mateusz Dziemian; Derek Duenas; Maxwell Lin; Justin Wang; Dan Hendrycks; Andy Zou; Zico Kolter; Matt Fredrikson; Eric Winsor; Jerome Wynne; Yarin Gal; Xander Davies
Training on Fake Labels: Mitigating Label Leakage in Split Learning via Secure Dimension Transformation. (62%)Yukun Jiang; Peiran Wang; Chengguo Lin; Ziyue Huang; Yong Cheng
PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning. (31%)Tingchen Fu; Mrinank Sharma; Philip Torr; Shay B. Cohen; David Krueger; Fazl Barez
AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation. (31%)Zijun Wang; Haoqin Tu; Jieru Mei; Bingchen Zhao; Yisen Wang; Cihang Xie
The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses. (16%)Grzegorz Głuch; Berkant Turan; Sai Ganesh Nagarajan; Sebastian Pokutta
Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbation. (4%)Saiful Islam Salim; Rubin Yuchan Yang; Alexander Cooper; Suryashree Ray; Saumya Debray; Sazzadur Rahaman
F2A: An Innovative Approach for Prompt Injection by Utilizing Feign Security Detection Agents. (1%)Yupeng Ren
RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process. (1%)Peiran Wang; Xiaogeng Liu; Chaowei Xiao
JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework. (1%)Fan Liu; Yue Feng; Zhao Xu; Lixin Su; Xinyu Ma; Dawei Yin; Hao Liu
2024-10-10
Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data. (99%)Binghui Li; Yuanzhi Li
Time Traveling to Defend Against Adversarial Example Attacks in Image Classification. (99%)Anthony Etim; Jakub Szefer
Understanding Adversarially Robust Generalization via Weight-Curvature Index. (98%)Yuelin Xu; Xiao Zhang
Invisibility Cloak: Disappearance under Human Pose Estimation via Backdoor Attacks. (92%)Minxing Zhang; Michael Backes; Xiao Zhang
A Survey on Physical Adversarial Attacks against Face Recognition Systems. (91%)Mingsi Wang; Jiachen Zhou; Tianlin Li; Guozhu Meng; Kai Chen
Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation. (74%)Tomas Bueno Momcilovic; Beat Buesser; Giulio Zizzo; Mark Purcell; Dian Balta
Bilinear MLPs enable weight-based mechanistic interpretability. (70%)Michael T. Pearce; Thomas Dooms; Alice Rigg; Jose M. Oramas; Lee Sharkey
Adversarial Robustness Overestimation and Instability in TRADES. (67%)Jonathan Weiping Li; Ren-Wei Liang; Cheng-Han Yeh; Cheng-Chang Tsai; Kuanchun Yu; Chun-Shien Lu; Shang-Tse Chen
RAB$^2$-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clients. (61%)Nuria Rodríguez-Barroso; M. Victoria Luzón; Francisco Herrera
Poison-splat: Computation Cost Attack on 3D Gaussian Splatting. (10%)Jiahao Lu; Yifan Zhang; Qiuhong Shen; Xinchao Wang; Shuicheng Yan
A Closer Look at Machine Unlearning for Large Language Models. (4%)Xiaojian Yuan; Tianyu Pang; Chao Du; Kejiang Chen; Weiming Zhang; Min Lin
2024-10-09
Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models. (99%)Yubo Wang; Chaohu Liu; Yanqiu Qu; Haoyu Cao; Deqiang Jiang; Linli Xu
Understanding Model Ensemble in Transferable Adversarial Attack. (99%)Wei Yao; Zeliang Zhang; Huayi Tang; Yong Liu
Secure Video Quality Assessment Resisting Adversarial Attacks. (75%)Ao-Xiang Zhang; Yu Ran; Weixuan Tang; Yuan-Gen Wang; Qingxiao Guan; Chunsheng Yang
Can DeepFake Speech be Reliably Detected? (62%)Hongbin Liu; Youzheng Chen; Arun Narayanan; Athula Balachandran; Pedro J. Moreno; Lun Wang
Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning. (15%)Wassim Bouaziz; El-Mahdi El-Mhamdi; Nicolas Usunier
Average Certified Radius is a Poor Metric for Randomized Smoothing. (11%)Chenhao Sun; Yuhao Mao; Mark Niklas Müller; Martin Vechev
JPEG Inspired Deep Learning. (11%)Ahmed H. Salamah; Kaixiang Zheng; Yiwen Liu; En-Hui Yang
Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility. (2%)Rajdeep Haldar; Yue Xing; Qifan Song; Guang Lin
Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates. (2%)Xiaosen Zheng; Tianyu Pang; Chao Du; Qian Liu; Jing Jiang; Min Lin
Mind Your Questions! Towards Backdoor Attacks on Text-to-Visualization Models. (2%)Shuaimin Li; Yuanfeng Song; Xuanang Chen; Anni Peng; Zhuoyue Wan; Chen Jason Zhang; Raymond Chi-Wing Wong
Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning. (1%)Runchuan Zhu; Zhipeng Ma; Jiang Wu; Junyuan Gao; Jiaqi Wang; Dahua Lin; Conghui He
AdaRC: Mitigating Graph Structure Shifts during Test-Time. (1%)Wenxuan Bao; Zhichen Zeng; Zhining Liu; Hanghang Tong; Jingrui He
PII-Scope: A Benchmark for Training Data PII Leakage Assessment in LLMs. (1%)Krishna Kanth Nakka; Ahmed Frikha; Ricardo Mendes; Xue Jiang; Xuebing Zhou
2024-10-08
Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models. (99%)Kangtao Lv; Huangsen Cao; Kainan Tu; Yihuai Xu; Zhimeng Zhang; Xin Ding; Yongwei Wang
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing. (98%)June Suk Choi; Kyungmin Lee; Jongheon Jeong; Saining Xie; Jinwoo Shin; Kimin Lee
Filtered Randomized Smoothing: A New Defense for Robust Modulation Classification. (98%)Wenhan Zhang; Meiyu Zhong; Ravi Tandon; Marwan Krunz
CALoR: Towards Comprehensive Model Inversion Defense. (76%)Hongyao Yu; Yixiang Qiu; Hao Fang; Bin Chen; Sijin Yu; Bin Wang; Shu-Tao Xia; Ke Xu
Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting. (74%)Nicholas Carlini; Jorge Chávez-Saab; Anna Hambitzer; Francisco Rodríguez-Henríquez; Adi Shamir
Training-free LLM-generated Text Detection by Mining Token Probability Sequences. (26%)Yihuai Xu; Yongwei Wang; Yifei Bi; Huangsen Cao; Zhouhan Lin; Yu Zhao; Fei Wu
PFAttack: Stealthy Attack Bypassing Group Fairness in Federated Learning. (10%)Jiashi Gao; Ziwei Wang; Xiangyu Zhao; Xin Yao; Xuetao Wei
Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations. (10%)Tarun Raheja; Nilay Pochhi
2024-10-07
TaeBench: Improving Quality of Toxic Adversarial Examples. (99%)Xuan Zhu; Dmitriy Bespalov; Liwen You; Ninad Kulkarni; Yanjun Qi
AnyAttack: Towards Large-scale Self-supervised Generation of Targeted Adversarial Examples for Vision-Language Models. (99%)Jiaming Zhang; Junhong Ye; Xingjun Ma; Yige Li; Yunfan Yang; Jitao Sang; Dit-Yan Yeung
LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles. (99%)Ali Ebrahimpour-Boroojeny; Hari Sundaram; Varun Chandrasekaran
Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models. (95%)Dehong Kong; Siyuan Liang; Xiaopeng Zhu; Yuansheng Zhong; Wenqi Ren
MIBench: A Comprehensive Benchmark for Model Inversion Attack and Defense. (86%)Yixiang Qiu; Hongyao Yu; Hao Fang; Wenbo Yu; Bin Chen; Xuan Wang; Shu-Tao Xia; Ke Xu
STOP! Camera Spoofing via the in-Vehicle IP Network. (83%)Dror Peri; Avishai Wool
Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models. (76%)Aye Phyu Phyu Aung; Xinrun Wang; Ruiyu Wang; Hau Chan; Bo An; Xiaoli Li; J. Senthilnath
Collaboration! Towards Robust Neural Methods for Routing Problems. (70%)Jianan Zhou; Yaoxin Wu; Zhiguang Cao; Wen Song; Jie Zhang; Zhiqi Shen
Aligning LLMs to Be Robust Against Prompt Injection. (47%)Sizhe Chen; Arman Zharmagambetov; Saeed Mahloujifar; Kamalika Chaudhuri; Chuan Guo
CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models. (11%)Songning Lai; Jiayu Yang; Yu Huang; Lijie Hu; Tianlang Xue; Zhangyi Hu; Jiaxu Li; Haicheng Liao; Yutao Yue
Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models. (8%)Xiao Yang; Kai Zhou; Yuni Lai; Gaolei Li
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation. (1%)Fanqing Meng; Jiaqi Liao; Xinyu Tan; Wenqi Shao; Quanfeng Lu; Kaipeng Zhang; Yu Cheng; Dianqi Li; Yu Qiao; Ping Luo
2024-10-06
Suspiciousness of Adversarial Texts to Human. (99%)Shakila Mahjabin Tonni; Pedro Faustini; Mark Dras
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning. (99%)Yongyi Su; Yushu Li; Nanqing Liu; Kui Jia; Xulei Yang; Chuan-Sheng Foo; Xun Xu
TA3: Testing Against Adversarial Attacks on Machine Learning Models. (67%)Yuanzhe Jin; Min Chen
Robustness Reprogramming for Representation Learning. (56%)Zhichao Hou; MohamadAli Torkamani; Hamid Krim; Xiaorui Liu
Towards Understanding and Enhancing Security of Proof-of-Training for DNN Model Ownership Verification. (2%)Yijia Chang; Hanrui Jiang; Chao Lin; Xinyi Huang; Jian Weng
Federated Learning Nodes Can Reconstruct Peers' Image Data. (1%)Ethan Wilson; Kai Yue; Chau-Wai Wong; Huaiyu Dai
2024-10-05
Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models. (38%)Yiting Dong; Guobin Shen; Dongcheng Zhao; Xiang He; Yi Zeng
ConDa: Fast Federated Unlearning with Contribution Dampening. (1%)Vikram S Chundawat; Pushkar Niroula; Prasanna Dhungana; Stefan Schoepf; Murari Mandal; Alexandra Brintrup
2024-10-04
Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization. (98%)Tung M. Luu; Thanh Nguyen; Tee Joshua Tian Jin; Sungwoon Kim; Chang D. Yoo
RAFT: Realistic Attacks to Fool Text Detectors. (96%)James Wang; Ran Li; Junfeng Yang; Chengzhi Mao
A Brain-Inspired Regularizer for Adversarial Robustness. (92%)Elie Attias; Cengiz Pehlevan; Dina Obeid
Gradient-based Jailbreak Images for Multimodal Fusion Models. (16%)Javier Rando; Hannah Korevaar; Erik Brinkman; Ivan Evtimov; Florian Tramèr
You Know What I'm Saying -- Jailbreak Attack via Implicit Reference. (16%)Tianyu Wu; Lingrui Mei; Ruibin Yuan; Lujun Li; Wei Xue; Yike Guo
Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective. (13%)Jonghyun Park; Juyeop Kim; Jong-Seok Lee
Make Interval Bound Propagation great again. (9%)Patryk Krukowski; Daniel Wilczak; Jacek Tabor; Anna Bielawska; Przemysław Spurek
Classification-Denoising Networks. (9%)Louis Thiry; Florentin Guth
Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs. (2%)Tomas Bueno Momcilovic; Dian Balta; Beat Buesser; Giulio Zizzo; Mark Purcell
BN-SCAFFOLD: controlling the drift of Batch Normalization statistics in Federated Learning. (1%)Gonzalo Iñaki Quintana; Laurence Vancamberg; Vincent Jugnon; Mathilde Mougeot; Agnès Desolneux
Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step. (1%)Wenxuan Wang; Kuiyi Gao; Zihan Jia; Youliang Yuan; Jen-tse Huang; Qiuzhi Liu; Shuai Wang; Wenxiang Jiao; Zhaopeng Tu
2024-10-03
SCA: Highly Efficient Semantic-Consistent Unrestricted Adversarial Attack. (99%)Zihao Pan; Weibin Wu; Yuhang Cao; Zibin Zheng
Towards Universal Certified Robustness with Multi-Norm Training. (26%)Enyi Jiang; Gagandeep Singh
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents. (15%)Hanrong Zhang; Jingyuan Huang; Kai Mei; Yifei Yao; Zhenting Wang; Chenlu Zhan; Hongwei Wang; Yongfeng Zhang
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs. (11%)Xiaogeng Liu; Peiran Li; Edward Suh; Yevgeniy Vorobeychik; Zhuoqing Mao; Somesh Jha; Patrick McDaniel; Huan Sun; Bo Li; Chaowei Xiao
Demonstration Attack against In-Context Learning for Code Intelligence. (10%)Yifei Ge; Weisong Sun; Yihang Lou; Chunrong Fang; Yiran Zhang; Yiming Li; Xiaofang Zhang; Yang Liu; Zhihong Zhao; Zhenyu Chen
Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors. (3%)Shuangpeng Han; Mengmi Zhang
Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models. (3%)Guobin Shen; Dongcheng Zhao; Yiting Dong; Xiang He; Yi Zeng
MTDNS: Moving Target Defense for Resilient DNS Infrastructure. (2%)Abdullah Aydeger; Pei Zhou; Sanzida Hoque; Marco Carvalho; Engin Zeydan
Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems. (1%)Guibin Zhang; Yanwei Yue; Zhixun Li; Sukwon Yun; Guancheng Wan; Kun Wang; Dawei Cheng; Jeffrey Xu Yu; Tianlong Chen
IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages? (1%)Akhilesh Aravapalli; Mounika Marreddy; Subba Reddy Oota; Radhika Mamidi; Manish Gupta
BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting. (1%)Xiao Lin; Zhining Liu; Dongqi Fu; Ruizhong Qiu; Hanghang Tong
Optimizing Adaptive Attacks against Content Watermarks for Language Models. (1%)Abdulrahman Diaa; Toluwani Aremu; Nils Lukas
Universally Optimal Watermarking Schemes for LLMs: from Theory to Practice. (1%)Haiyun He; Yepeng Liu; Ziqiao Wang; Yongyi Mao; Yuheng Bu
Buckle Up: Robustifying LLMs at Every Customization Stage via Data Curation. (1%)Xiaoqun Liu; Jiacheng Liang; Luoxi Tang; Chenyu You; Muchao Ye; Zhaohan Xi
2024-10-02
On Using Certified Training towards Empirical Robustness. (99%)Palma Alessandro De; Serge Durand; Zakaria Chihani; François Terrier; Caterina Urban
Impact of White-Box Adversarial Attacks on Convolutional Neural Networks. (99%)Rakesh Podder; Sudipto Ghosh
Signal Adversarial Examples Generation for Signal Detection Network via White-Box Attack. (99%)Dongyang Li; Linyuan Wang; Guangwei Xiong; Bin Yan; Dekui Ma; Jinxian Peng
MOREL: Enhancing Adversarial Robustness through Multi-Objective Representation Learning. (99%)Sedjro Salomon Hotegni; Sebastian Peitz
Fake It Until You Break It: On the Adversarial Robustness of AI-generated Image Detectors. (98%)Sina Mavali; Jonas Ricker; David Pape; Yash Sharma; Asja Fischer; Lea Schönherr
"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning. (93%)Jiale Zhang; Chengcheng Zhu; Bosen Rao; Hao Sui; Xiaobing Sun; Bing Chen; Chunyi Zhou; Shouling Ji
Social Media Authentication and Combating Deepfakes using Semi-fragile Invisible Image Watermarking. (82%)Aakash Varma Nadimpalli; Ajita Rattani
The Unlikely Hero: Nonideality in Analog Photonic Neural Networks as Built-in Defender Against Adversarial Attacks. (76%)Haotian Lu; Ziang Yin; Partho Bhoumik; Sanmitra Banerjee; Krishnendu Chakrabarty; Jiaqi Gu
BadCM: Invisible Backdoor Attack Against Cross-Modal Learning. (13%)Zheng Zhang; Xu Yuan; Lei Zhu; Jingkuan Song; Liqiang Nie
Controlled Generation of Natural Adversarial Documents for Stealthy Retrieval Poisoning. (13%)Collin Zhang; Tingwei Zhang; Vitaly Shmatikov
Automated Red Teaming with GOAT: the Generative Offensive Agent Tester. (11%)Maya Pavlova; Erik Brinkman; Krithika Iyer; Vitor Albiero; Joanna Bitton; Hailey Nguyen; Joe Li; Cristian Canton Ferrer; Ivan Evtimov; Aaron Grattafiori
Information-Theoretical Principled Trade-off between Jailbreakability and Stealthiness on Vision Language Models. (8%)Ching-Chia Kao; Chia-Mu Yu; Chun-Shien Lu; Chu-Song Chen
One Wave to Explain Them All: A Unifying Perspective on Post-hoc Explainability. (1%)Gabriel Kasmi; Amandine Brunetto; Thomas Fel; Jayneel Parekh
2024-10-01
Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective. (54%)Yixin Liu; Arielle Carr; Lichao Sun
Adversarial Suffixes May Be Features Too! (15%)Wei Zhao; Zhe Li; Yige Li; Jun Sun
2024-09-30
Characterizing Model Robustness via Natural Input Gradients. (92%)Adrián Rodríguez-Muñoz; Tongzhou Wang; Antonio Torralba
Robust LLM safeguarding via refusal feature adversarial training. (80%)Lei Yu; Virginie Do; Karen Hambardzumyan; Nicola Cancedda
Resonance Reduction Against Adversarial Attacks in Dynamic Networks via Eigenspectrum Optimization. (76%)Alp Sahin; Nicolas Kozachuk; Rick S. Blum; Subhrajit Bhattacharya
Navigating Threats: A Survey of Physical Adversarial Attacks on LiDAR Perception Systems in Autonomous Vehicles. (45%)Amira Guesmi; Muhammad Shafique
VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data. (8%)Xuefeng Du; Reshmi Ghosh; Robert Sim; Ahmed Salem; Vitor Carvalho; Emily Lawton; Yixuan Li; Jack W. Stokes
2024-09-29
MASKDROID: Robust Android Malware Detection with Masked Graph Representations. (99%)Jingnan Zheng; Jiaohao Liu; An Zhang; Jun Zeng; Ziqi Yang; Zhenkai Liang; Tat-Seng Chua
Adversarial Examples for DNA Classification. (98%)Hyunwoo Yoo
Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises. (86%)Anubhooti Jain; Susim Roy; Kwanit Gupta; Mayank Vatsa; Richa Singh
BadHMP: Backdoor Attack against Human Motion Prediction. (61%)Chaohui Xu; Si Wang; Chip-Hong Chang
Nonideality-aware training makes memristive networks more robust to adversarial attacks. (38%)Dovydas Joksas; Luis Muñoz-González; Emil Lupu; Adnan Mehonic
Infighting in the Dark: Multi-Labels Backdoor Attack in Federated Learning. (33%)Ye Li; Yanchao Zhao; Chengcheng Zhu; Jiale Zhang
Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology. (10%)Son Quoc Tran; Matt Kretchmar
Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances. (5%)Hanyang Hu; Xilun Zhang; Xubo Lyu; Mo Chen
IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding. (1%)Pengcheng Li; Xulong Zhang; Jing Xiao; Jianzong Wang
Can Models Learn Skill Composition from Examples? (1%)Haoyu Zhao; Simran Kaur; Dingli Yu; Anirudh Goyal; Sanjeev Arora
2024-09-28
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats. (74%)Kuanrong Liu; Siyuan Liang; Jiawei Liang; Pengwen Dai; Xiaochun Cao
GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks. (13%)Rongchang Li; Minjie Chen; Chang Hu; Han Chen; Wenpeng Xing; Meng Han
Leveraging MTD to Mitigate Poisoning Attacks in Decentralized FL with Non-IID Data. (11%)Chao Feng; Alberto Huertas Celdrán; Zien Zeng; Zi Ye; der Assen Jan von; Gerome Bovet; Burkhard Stiller
Survey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce. (2%)Carl E. J. Brodzinski
Privacy Attack in Federated Learning is Not Easy: An Experimental Study. (1%)Hangyu Zhu; Liyuan Huang; Zhenping Xie
2024-09-27
Adversarial Challenges in Network Intrusion Detection Systems: Research Insights and Future Prospects. (96%)Sabrine Ennaji; Gaspari Fabio De; Dorjan Hitaj; Alicia K/Bidi; Luigi V. Mancini
Enhancing Robustness of Graph Neural Networks through p-Laplacian. (12%)Anuj Kumar Sirohi; Subhanu Halder; Kabir Kumar; Sandeep Kumar
Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators. (1%)Seyedarmin Azizi; Mohammad Erfan Sadeghi; Mehdi Kamal; Massoud Pedram
In-depth Analysis of Privacy Threats in Federated Learning for Medical Data. (1%)Badhan Chandra Das; M. Hadi Amini; Yanzhao Wu
2024-09-26
Showing Many Labels in Multi-label Classification Models: An Empirical Study of Adversarial Examples. (98%)Yujiang Liu; Wenjian Luo; Zhijian Chen; Muhammad Luqman Naseem
Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization. (98%)Yunpeng Gong; Qingyuan Zeng; Dejun Xu; Zhenzhong Wang; Min Jiang
Discovering New Shadow Patterns for Black-Box Attacks on Lane Detection of Autonomous Vehicles. (97%)Pedram MohajerAnsari; Alkim Domeke; Voor Jan de; Arkajyoti Mitra; Grace Johnson; Amir Salarpour; Habeeb Olufowobi; Mohammad Hamad; Mert D. Pesé
Improving Fast Adversarial Training via Self-Knowledge Guidance. (82%)Chengze Jiang; Junkai Wang; Minjing Dong; Jie Gui; Xinli Shi; Yuan Cao; Yuan Yan Tang; James Tin-Yau Kwok
Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations. (69%)Supriya Manna; Niladri Sett
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning. (69%)Yuan Xun; Siyuan Liang; Xiaojun Jia; Xinwei Liu; Xiaochun Cao
DarkSAM: Fooling Segment Anything Model to Segment Nothing. (68%)Ziqi Zhou; Yufei Song; Minghui Li; Shengshan Hu; Xianlong Wang; Leo Yu Zhang; Dezhong Yao; Hai Jin
Perturb, Attend, Detect and Localize (PADL): Robust Proactive Image Defense. (56%)Filippo Bartolucci; Iacopo Masi; Giuseppe Lisanti
Development of an Edge Resilient ML Ensemble to Tolerate ICS Adversarial Attacks. (54%)Likai Yao; Qinxuan Shi; Zhanglong Yang; Sicong Shao; Salim Hariri
Backdoor Attacks for LLMs with Weak-To-Strong Knowledge Distillation. (15%)Shuai Zhao; Leilei Gan; Zhongliang Guo; Xiaobao Wu; Luwei Xiao; Xiaoyu Xu; Cong-Duy Nguyen; Luu Anh Tuan
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey. (15%)Tiansheng Huang; Sihao Hu; Fatih Ilhan; Selim Furkan Tekin; Ling Liu
Dark Miner: Defend against unsafe generation for text-to-image diffusion models. (5%)Zheling Meng; Bo Peng; Xiaochuan Jin; Yue Jiang; Jing Dong; Wei Wang; Tieniu Tan
An Adversarial Perspective on Machine Unlearning for AI Safety. (2%)Jakub Łucki; Boyi Wei; Yangsibo Huang; Peter Henderson; Florian Tramèr; Javier Rando
Revolutionizing Payload Inspection: A Self-Supervised Journey to Precision with Few Shots. (2%)Kyle Stein; Arash Mahyari; Guillermo III Francia; Eman El-Sheikh
2024-09-25
Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System. (93%)Kaike Zhang; Qi Cao; Yunfan Wu; Fei Sun; Huawei Shen; Xueqi Cheng
A Hybrid Quantum-Classical AI-Based Detection Strategy for Generative Adversarial Network-Based Deepfake Attacks on an Autonomous Vehicle Traffic Sign Classification System. (82%)M Sabbir Salek; Shaozhi Li; Mashrur Chowdhury
RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking. (75%)Yifan Jiang; Kriti Aggarwal; Tanmay Laud; Kashif Munir; Jay Pujara; Subhabrata Mukherjee
Transient Adversarial 3D Projection Attacks on Object Detection in Autonomous Driving. (67%)Ce Zhou; Qiben Yan; Sijia Liu
Examining the Rat in the Tunnel: Interpretable Multi-Label Classification of Tor-based Malware. (45%)Ishan Karunanayake; Mashael AlSabah; Nadeem Ahmed; Sanjay Jha
SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection. (38%)Guanyi Mou; Pengyi Ye; Kyumin Lee
SHEATH: Defending Horizontal Collaboration for Distributed CNNs against Adversarial Noise. (22%)Muneeba Asif; Mohammad Kumail Kazmi; Mohammad Ashiqur Rahman; Syed Rafay Hasan; Soamar Homsi
Claim-Guided Textual Backdoor Attack for Practical Applications. (10%)Minkyoo Song; Hanna Kim; Jaehan Kim; Youngjin Jin; Seungwon Shin
Cat-and-Mouse Satellite Dynamics: Divergent Adversarial Reinforcement Learning for Contested Multi-Agent Space Operations. (1%)Cameron Mehlman; Joseph Abramov; Gregory Falco
2024-09-24
Adversarial Backdoor Defense in CLIP. (99%)Junhao Kuang; Siyuan Liang; Jiawei Liang; Kuanrong Liu; Xiaochun Cao
Revisiting Acoustic Features for Robust ASR. (84%)Muhammad A. Shah; Bhiksha Raj
Adversarial Watermarking for Face Recognition. (80%)Yuguang Yao; Anil Jain; Sijia Liu
Proactive Schemes: A Survey of Adversarial Attacks for Social Good. (54%)Vishal Asnani; Xi Yin; Xiaoming Liu
Privacy Evaluation Benchmarks for NLP Models. (45%)Wei Huang; Yinggui Wang; Cen Chen
Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis. (33%)Xianda Zhang; Siyuan Liang
PACE: Poisoning Attacks on Learned Cardinality Estimation. (4%)Jintao Tsinghua University Zhang; Chao Tsinghua University Zhang; Guoliang Tsinghua University Li; Chengliang Beijing Institute of Technology Chai
2024-09-23
Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training. (96%)Jinpeng Lin; Xulei Yang; Tianrui Li; Xun Xu
Interpretability-Guided Test-Time Adversarial Defense. (87%)Akshay Kulkarni; Tsui-Wei Weng
Effective and Evasive Fuzz Testing-Driven Jailbreaking Attacks against LLMs. (87%)Xueluan Gong; Mingzhe Li; Yilin Zhang; Fengyuan Ran; Chen Chen; Yanjiao Chen; Qian Wang; Kwok-Yan Lam
Data Poisoning-based Backdoor Attack Framework against Supervised Learning Rules of Spiking Neural Networks. (68%)Lingxin Jin; Meiyu Lin; Wei Jiang; Jinyu Zhan
Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI. (47%)Ambrish Rawat; Stefan Schoepf; Giulio Zizzo; Giandomenico Cornacchia; Muhammad Zaid Hameed; Kieran Fraser; Erik Miehling; Beat Buesser; Elizabeth M. Daly; Mark Purcell; Prasanna Sattigeri; Pin-Yu Chen; Kush R. Varshney
PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs. (33%)Jiahao Yu; Yangguang Shao; Hanwen Miao; Junzheng Shi; Xinyu Xing
Log-normal Mutations and their Use in Detecting Surreptitious Fake Images. (13%)Ismail Labiad; Thomas Bäck; Pierre Fernandez; Laurent Najman; Tom Sander; Furong Ye; Mariia Zameshina; Olivier Teytaud
Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving. (12%)Ehsan Ahmadi; Ray Mercurius; Soheil Alizadeh; Kasra Rezaee; Amir Rasouli
Toward Mixture-of-Experts Enabled Trustworthy Semantic Communication for 6G Networks. (5%)Jiayi He; Xiaofeng Luo; Jiawen Kang; Hongyang Du; Zehui Xiong; Ci Chen; Dusit Niyato; Xuemin Shen
Room Impulse Responses help attackers to evade Deep Fake Detection. (1%)Hieu-Thi Luong; Duc-Tuan Truong; Kong Aik Lee; Eng Siong Chng
AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark. (1%)Michal Nazarczuk; Thomas Tanay; Sibi Catley-Chandar; Richard Shaw; Radu Timofte; Eduardo Pérez-Pellitero
UTrace: Poisoning Forensics for Private Collaborative Learning. (1%)Evan Rose; Hidde Lycklama; Harsh Chaudhari; Anwar Hithnawi; Alina Oprea
SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning. (1%)Minyeong Choe; Cheolhee Park; Changho Seo; Hyunil Kim
2024-09-22
Enhancing LLM-based Autonomous Driving Agents to Mitigate Perception Attacks. (10%)Ruoyu Song; Muslum Ozgur Ozmen; Hyungsub Kim; Antonio Bianchi; Z. Berkay Celik
Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions. (1%)Hongchen Wang; Kangming Li; Scott Ramsay; Yao Fehlis; Edward Kim; Jason Hattrick-Simpers
2024-09-21
Cloud Adversarial Example Generation for Remote Sensing Image Classification. (99%)Fei Ma; Yuqiang Feng; Fan Zhang; Yongsheng Zhou
Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation. (98%)G M Shahariar; Jia Chen; Jiachen Li; Yue Dong
When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning. (69%)Naheed Anjum Arafat; Debabrota Basu; Yulia Gel; Yuzhou Chen
PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach. (62%)Zhihao Lin; Wei Ma; Mingyi Zhou; Yanjie Zhao; Haoyu Wang; Yang Liu; Jun Wang; Li Li
ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination. (10%)Navid Ayoobi; Lily Knab; Wen Cheng; David Pantoja; Hamidreza Alikhani; Sylvain Flamant; Jin Kim; Arjun Mukherjee
Perfect Gradient Inversion in Federated Learning: A New Paradigm from the Hidden Subset Sum Problem. (8%)Qiongxiu Li; Lixia Luo; Agnese Gini; Changlong Ji; Zhanhao Hu; Xiao Li; Chengfang Fang; Jie Shi; Xiaolin Hu
Data-centric NLP Backdoor Defense from the Lens of Memorization. (4%)Zhenting Wang; Zhizhi Wang; Mingyu Jin; Mengnan Du; Juan Zhai; Shiqing Ma
2024-09-20
Efficient Visualization of Neural Networks with Generative Models and Adversarial Perturbations. (99%)Athanasios Karagounis
ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformer. (99%)Shihua Sun; Kenechukwu Nwodo; Shridatt Sugrim; Angelos Stavrou; Haining Wang
Certified Adversarial Robustness via Partition-based Randomized Smoothing. (81%)Hossein Goli; Farzan Farnia
ID-Guard: A Universal Framework for Combating Facial Manipulation via Breaking Identification. (76%)Zuomin Qu; Wei Lu; Xiangyang Luo; Qian Wang; Xiaochun Cao
Persistent Backdoor Attacks in Continual Learning. (73%)Zhen Guo; Abhinav Kumar; Reza Tourani
Relationship between Uncertainty in DNNs and Adversarial Attacks. (70%)Abigail Adeniran; Adewale Adeyemo
PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models. (61%)Vu Tuan Truong; Long Bao Le
On the Feasibility of Fully AI-automated Vishing Attacks. (1%)João Figueiredo; Afonso Carvalho; Daniel Castro; Daniel Gonçalves; Nuno Santos
2024-09-19
Deep generative models as an adversarial attack strategy for tabular machine learning. (99%)Salijona Dyrmishi; Mihaela Cătălina Stoian; Eleonora Giunchiglia; Maxime Cordy
TEAM: Temporal Adversarial Examples Attack Model against Network Intrusion Detection System Applied to RNN. (99%)Ziyi Liu; Dengpan Ye; Long Tang; Yunming Zhang; Jiacheng Deng
Hidden Activations Are Not Enough: A General Approach to Neural Network Predictions. (98%)Samuel Leblanc; Aiky Rasolomanana; Marco Armenta
Defending against Reverse Preference Attacks is Difficult. (83%)Domenic Rosati; Giles Edkins; Harsh Raj; David Atanasov; Subhabrata Majumdar; Janarthanan Rajendran; Frank Rudzicz; Hassan Sajjad
Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation. (45%)Tsung-Han Wu; Hung-Ting Su; Shang-Tse Chen; Winston H. Hsu
VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness. (26%)Xuan Cai; Zhiyong Cui; Xuesong Bai; Ruimin Ke; Zhenshu Ma; Haiyang Yu; Yilong Ren
Data Poisoning and Leakage Analysis in Federated Learning. (11%)Wenqi Wei; Tiansheng Huang; Zachary Yahn; Anoop Singhal; Margaret Loper; Ling Liu
Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models. (2%)Hao Cheng; Erjia Xiao; Chengyuan Yu; Zhao Yao; Jiahang Cao; Qiang Zhang; Jiaxu Wang; Mengshu Sun; Kaidi Xu; Jindong Gu; Renjing Xu
Hidden in Plain Sound: Environmental Backdoor Poisoning Attacks on Whisper, and Mitigations. (2%)Jonatan Bartolini; Todor Stoyanov; Alberto Giaretta
2024-09-18
Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach. (99%)Nastaran Darabi; Dinithi Jayasuriya; Devashri Naik; Theja Tulabandhula; Amit Ranjan Trivedi
ITPatch: An Invisible and Triggered Physical Adversarial Patch against Traffic Sign Recognition. (99%)Shuai Yuan; Hongwei Li; Xingshuo Han; Guowen Xu; Wenbo Jiang; Tao Ni; Qingchuan Zhao; Yuguang Fang
NPAT Null-Space Projected Adversarial Training Towards Zero Deterioration. (96%)Hanyi Hu; Qiao Han; Kui Chen; Yao Yang
LLM-Powered Text Simulation Attack Against ID-Free Recommender Systems. (76%)Zongwei Wang; Min Gao; Junliang Yu; Xinyi Gao; Quoc Viet Hung Nguyen; Shazia Sadiq; Hongzhi Yin
PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning. (68%)Yukai Xu; Yujie Gu; Kouichi Sakurai
A constrained optimization approach to improve robustness of neural networks. (54%)Shudian Zhao; Jan Kronqvist
Understanding Implosion in Text-to-Image Generative Models. (2%)Wenxin Ding; Cathy Y. Li; Shawn Shan; Ben Y. Zhao; Haitao Zheng
2024-09-17
Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classification. (98%)Deepsayan Sadhukhan; Nitin Priyadarshini Shankar; Sheetal Kalyani
EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage. (76%)Zeyi Liao; Lingbo Mo; Chejian Xu; Mintong Kang; Jiawei Zhang; Chaowei Xiao; Yuan Tian; Bo Li; Huan Sun
Contextual Breach: Assessing the Robustness of Transformer-based QA Models. (56%)Asir Saadat; Nahian Ibn Asad; Md Farhan Ishmam
Hard-Label Cryptanalytic Extraction of Neural Network Models. (2%)Yi Chen; Xiaoyang Dong; Jian Guo; Yantian Shen; Anyu Wang; Xiaoyun Wang
2024-09-16
Towards Physically-Realizable Adversarial Attacks in Embodied Vision Navigation. (82%)Meng Chen; Jiawei Tu; Chao Qi; Yonghao Dang; Feng Zhou; Wei Wei; Jianqin Yin
CaBaGe: Data-Free Model Extraction using ClAss BAlanced Generator Ensemble. (2%)Jonathan Rosenthal; Shanchao Liang; Kevin Zhang; Lin Tan
Realistic Extreme Behavior Generation for Improved AV Testing. (1%)Robert Dyro; Matthew Foutter; Ruolin Li; Lillo Luigi Di; Edward Schmerling; Xilin Zhou; Marco Pavone
Jailbreaking Large Language Models with Symbolic Mathematics. (1%)Emet Bethany; Mazal Bethany; Juan Arturo Nolazco Flores; Sumit Kumar Jha; Peyman Najafirad
Speaker Contrastive Learning for Source Speaker Tracing. (1%)Qing Wang; Hongmei Guo; Jian Kang; Mengjie Du; Jie Li; Xiao-Lei Zhang; Lei Xie
2024-09-15
Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective. (98%)Ningfei Wang; Shaoyuan Xie; Takami Sato; Yunpeng Luo; Kaidi Xu; Qi Alfred Chen
Federated Learning in Adversarial Environments: Testbed Design and Poisoning Resilience in Cybersecurity. (8%)Hao Jian Huang; Bekzod Iskandarov; Mizanur Rahman; Hakan T. Otal; M. Abdullah Canbaz
2024-09-14
Real-world Adversarial Defense against Patch Attacks based on Diffusion Model. (99%)Xingxing Wei; Caixin Kang; Yinpeng Dong; Zhengyi Wang; Shouwei Ruan; Yubo Chen; Hang Su
2024-09-13
XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution. (95%)Kiana Vu; Phung Lai; Truc Nguyen
Are Existing Road Design Guidelines Suitable for Autonomous Vehicles? (41%)Yang Sun; Christopher M. Poskitt; Jun Sun
Clean Label Attacks against SLU Systems. (31%)Henry Li Xinyuan; Sonal Joshi; Thomas Thebaud; Jesus Villalba; Najim Dehak; Sanjeev Khudanpur
FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection. (15%)Jialuo Chen; Jingyi Wang; Xiyue Zhang; Youcheng Sun; Marta Kwiatkowska; Jiming Chen; Peng Cheng
2024-09-12
LoRID: Low-Rank Iterative Diffusion for Adversarial Purification. (99%)Geigh Zollicoffer; Minh Vu; Ben Nebgen; Juan Castorena; Boian Alexandrov; Manish Bhattarai
High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis. (93%)Takuto Onikubo; Yusuke Matsui
FedProphet: Memory-Efficient Federated Adversarial Training via Theoretic-Robustness and Low-Inconsistency Cascade Learning. (92%)Minxue Tang; Yitu Wang; Jingyang Zhang; Louis DiValentin; Aolin Ding; Amin Hass; Yiran Chen; Hai "Helen" Li
Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised Defense. (73%)Jeremy Styborski; Mingzhi Lyu; Yi Huang; Adams Kong
Sub-graph Based Diffusion Model for Link Prediction. (9%)Hang Li; Wei Jin; Geri Skenderi; Harry Shomer; Wenzhuo Tang; Wenqi Fan; Jiliang Tang
Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking. (1%)Stav Cohen; Ron Bitton; Ben Nassi
Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights. (1%)Dixi Yao
2024-09-11
Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving. (99%)Tianyuan Zhang; Lu Wang; Jiaqi Kang; Xinwei Zhang; Siyuan Liang; Yuwei Chen; Aishan Liu; Xianglong Liu
Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks. (98%)Md Zarif Hossain; Ahmed Imteaj
Introducing Perturb-ability Score (PS) to Enhance Robustness Against Evasion Adversarial Attacks on ML-NIDS. (97%)Mohamed elShehaby; Ashraf Matrawy
D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack. (93%)Hong-Hanh Nguyen-Le; Van-Tuan Tran; Dinh-Thuc Nguyen; Nhien-An Le-Khac
A Cost-Aware Approach to Adversarial Robustness in Neural Networks. (84%)Charles Meyers; Mohammad Reza Saleh Sedghpour; Tommy Löfstedt; Erik Elmroth
Attack End-to-End Autonomous Driving through Module-Wise Noise. (74%)Lu Wang; Tianyuan Zhang; Yikai Han; Muyang Fang; Ting Jin; Jiaqi Kang
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains. (67%)Xun Xian; Ganghua Wang; Xuan Bi; Jayanth Srinivasa; Ashish Kundu; Charles Fleming; Mingyi Hong; Jie Ding
Enhancing adversarial robustness in Natural Language Inference using explanations. (67%)Alexandros Koulakos; Maria Lymperaiou; Giorgos Filandrianos; Giorgos Stamou
AdvLogo: Adversarial Patch Attack against Object Detectors based on Diffusion Models. (64%)Boming Miao; Chunxiao Li; Yao Zhu; Weixiang Sun; Zizhe Wang; Xiaoyi Wang; Chuanlong Xie
Understanding Knowledge Drift in LLMs through Misinformation. (1%)Alina Fastowski; Gjergji Kasneci
2024-09-10
Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models. (99%)Siyu Zhai; Zhibo He; Xiaofeng Cong; Junming Hou; Jie Gui; Jian Wei You; Xin Gong; James Tin-Yau Kwok; Yuan Yan Tang
Advancing Hybrid Defense for Byzantine Attacks in Federated Learning. (84%)Kai Yue; Richeng Jin; Chau-Wai Wong; Huaiyu Dai
Adversarial Attacks to Multi-Modal Models. (76%)Zhihao Dou; Xin Hu; Haibo Yang; Zhuqing Liu; Minghong Fang
DV-FSR: A Dual-View Target Attack Framework for Federated Sequential Recommendation. (67%)Qitao Qin; Yucong Luo; Mingyue Cheng; Qingyang Mao; Chenyi Lei
2024-09-09
Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs. (99%)Yahya Jabary; Andreas Plesner; Turlan Kuzhagaliyev; Roger Wattenhofer
Adversarial Attacks on Data Attribution. (99%)Xinhe Wang; Pingbang Hu; Junwei Deng; Jiaqi W. Ma
Input Space Mode Connectivity in Deep Neural Networks. (83%)Jakub Vrabel; Ori Shem-Ur; Yaron Oz; David Krueger
Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Models. (83%)Aakash Sen Sharma; Niladri Sarkar; Vikram Chundawat; Ankur A Mali; Murari Mandal
On the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective. (33%)Aoting Hu; Yanzhi Chen; Renjie Xie; Adrian Weller
2024-09-08
PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions. (99%)Yudong Zhang; Ruobing Xie; Jiansheng Chen; Xingwu Sun; Yu Wang
2DSig-Detect: a semi-supervised framework for anomaly detection on image data using 2D-signatures. (87%)Xinheng Xie; Kureha Yamaguchi; Margaux Leblanc; Simon Malzard; Varun Chhabra; Victoria Nockles; Yue Wu
Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation. (67%)Yanni Xue; Haojie Hao; Jiakai Wang; Qiang Sheng; Renshuai Tao; Yu Liang; Pu Feng; Xianglong Liu
Natias: Neuron Attribution based Transferable Image Adversarial Steganography. (67%)Zexin Fan; Kejiang Chen; Kai Zeng; Jiansong Zhang; Weiming Zhang; Nenghai Yu
2024-09-07
Phrase-Level Adversarial Training for Mitigating Bias in Neural Network-based Automatic Essay Scoring. (86%)Haddad Philip; Tsegaye Misikir Tashu
PIXHELL Attack: Leaking Sensitive Information from Air-Gap Computers via `Singing Pixels'. (80%)Mordechai Guri
Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation. (12%)Lars Nieradzik; Henrike Stephani; Janis Keuper
2024-09-06
Learning to Learn Transferable Generative Attack for Person Re-Identification. (99%)Yuan Bian; Min Liu; Xueping Wang; Yunfeng Ma; Yaonan Wang
PANTS: Practical Adversarial Network Traffic Samples against ML-powered Networking Classifiers. (99%)Minhao Jin; Maria Apostolaki
Secure Traffic Sign Recognition: An Attention-Enabled Universal Image Inpainting Mechanism against Light Patch Attacks. (83%)Hangcheng Cao; Longzhi Yuan; Guowen Xu; Ziyang He; Zhengru Fang; Yuguang Fang
Mind The Gap: Can Air-Gaps Keep Your Private Data Secure? (74%)Mordechai Guri
Exploiting the Data Gap: Utilizing Non-ignorable Missingness to Manipulate Model Learning. (38%)Deniz Koyuncu; Alex Gittens; Bülent Yener; Moti Yung
Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers. (8%)Gorka Abad; Stjepan Picek; Lorenzo Cavallaro; Aitor Urbieta
Dual-stream Feature Augmentation for Domain Generalization. (8%)Shanshan Wang; ALuSi; Xun Yang; Ke Xu; Huibin Tan; Xingyi Zhang
2024-09-05
A practical approach to evaluating the adversarial distance for machine learning classifiers. (98%)Georg Siedel; Ekagra Gupta; Andrey Morozov
Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks. (92%)Akshay Jain; Shiv Ram Dubey; Satish Kumar Singh; KC Santosh; Bidyut Baran Chaudhuri
Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG. (31%)Manshan Guo; Bhavin Choksi; Sari Sadiya; Alessandro T. Gifford; Martina G. Vilas; Radoslaw M. Cichy; Gemma Roig
Recent Advances in Attack and Defense Approaches of Large Language Models. (4%)Jing Cui; Yishi Xu; Zhewei Huang; Shuchang Zhou; Jianbin Jiao; Junge Zhang
WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking. (3%)Carl De Sousa Trias; Mihai Mitrea; Attilio Fiandrotti; Marco Cagnazzo; Sumanta Chaudhuri; Enzo Tartaglione
Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm? (1%)Rui Wen; Michael Backes; Yang Zhang
2024-09-04
Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers. (99%)Zuquan Peng; Yuanyuan He; Jianbing Ni; Ben Niu
OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation. (99%)Włodzimierz Lewoniewski; Piotr Stolarski; Milena Stróżyna; Elzbieta Lewańska; Aleksandra Wojewoda; Ewelina Księżniak; Marcin Sawiński
TASAR: Transferable Attack on Skeletal Action Recognition. (92%)Yunfeng Diao; Baiqi Wu; Ruixuan Zhang; Ajian Liu; Xingxing Wei; Meng Wang; He Wang
Adversarial Attacks on Machine Learning-Aided Visualizations. (83%)Takanori Fujiwara; Kostiantyn Kucher; Junpeng Wang; Rafael M. Martins; Andreas Kerren; Anders Ynnerman
Transfer-based Adversarial Poisoning Attacks for Online (MIMO-)Deep Receviers. (76%)Kunze Wu; Weiheng Jiang; Dusit Niyato; Yinghuan Li; Chuang Luo
Boosting Certificate Robustness for Time Series Classification with Efficient Self-Ensemble. (70%)Chang Dong; Zhengyang Li; Liangwei Zheng; Weitong Chen; Wei Emma Zhang
AdvSecureNet: A Python Toolkit for Adversarial Machine Learning. (33%)Melih Catal; Manuel Günther
Active Fake: DeepFake Camouflage. (13%)Pu Sun; Honggang Qi; Yuezun Li
Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA). (2%)Alan Aqrawi
2024-09-03
Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor. (97%)Abdullah Arafat Miah; Yu Bi
Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge. (92%)Hyejin Park; Dongbo Min
NoiseAttack: An Evasive Sample-Specific Multi-Targeted Backdoor Attack Through White Gaussian Noise. (16%)Abdullah Arafat Miah; Kaan Icer; Resit Sendag; Yu Bi
Reassessing Noise Augmentation Methods in the Context of Adversarial Speech. (5%)Karla Pizzi; Matías Pizarro; Asja Fischer
On the Vulnerability of Skip Connections to Model Inversion Attacks. (3%)Jun Hao Koh; Sy-Tuyen Ho; Ngoc-Bao Nguyen; Ngai-man Cheung
2024-09-02
One-Index Vector Quantization Based Adversarial Attack on Image Classification. (99%)Haiju Fan; Xiaona Qin; Shuang Chen; Hubert P. H. Shum; Ming Li
Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness. (99%)Giorgio Piras; Maura Pintor; Ambra Demontis; Battista Biggio; Giorgio Giacinto; Fabio Roli
Phantom: Untargeted Poisoning Attacks on Semi-Supervised Learning (Full Version). (68%)Jonathan Knauer; Phillip Rieger; Hossein Fereidooni; Ahmad-Reza Sadeghi
Defending against Model Inversion Attacks via Random Erasing. (64%)Viet-Hung Tran; Ngoc-Bao Nguyen; Son T. Mai; Hans Vandierendonck; Ngai-man Cheung
CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models. (62%)Rui Zeng; Xi Chen; Yuwen Pu; Xuhong Zhang; Tianyu Du; Shouling Ji
Purification-Agnostic Proxy Learning for Agentic Copyright Watermarking against Adversarial Evidence Forgery. (26%)Erjin Bao; Ching-Chun Chang; Hanrui Wang; Isao Echizen
Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack. (26%)Guanzhong Chen; Zhenghan Qin; Mingxin Yang; Yajie Zhou; Tao Fan; Tianyu Du; Zenglin Xu
A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches. (16%)Kim Jinwoo
Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classification. (1%)Kangdao Liu; Tianhao Sun; Hao Zeng; Yongshan Zhang; Chi-Man Pun; Chi-Man Vong
2024-09-01
Comprehensive Botnet Detection by Mitigating Adversarial Attacks, Navigating the Subtleties of Perturbation Distances and Fortifying Predictions with Conformal Layers. (99%)Rahul Yumlembam; Biju Issac; Seibu Mary Jacob; Longzhi Yang
Accurate Forgetting for All-in-One Image Restoration Model. (83%)Xin Su; Zhuoran Zheng
The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs. (26%)Bocheng Chen; Hanqing Guo; Guangjing Wang; Yuanda Wang; Qiben Yan
Fisher Information guided Purification against Backdoor Attacks. (12%)Nazmul Karim; Abdullah Al Arafat; Adnan Siraj Rakin; Zhishan Guo; Nazanin Rahnavard
2024-08-31
HSF: Defending against Jailbreak Attacks with Hidden State Filtering. (75%)Cheng Qian; Hainan Zhang; Lei Sha; Zhiming Zheng
Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks. (15%)Yu He; Boheng Li; Yao Wang; Mengda Yang; Juan Wang; Hongxin Hu; Xingyu Zhao
Robust off-policy Reinforcement Learning via Soft Constrained Adversary. (4%)Kosuke Nakanishi; Akihiro Kubo; Yuji Yasui; Shin Ishii
2024-08-30
LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models. (92%)Hossein Khalili; Seongbin Park; Vincent Li; Brandan Bright; Ali Payani; Ramana Rao Kompella; Nader Sehatbakhsh
Instant Adversarial Purification with Adversarial Consistency Distillation. (33%)Chun Tong Lei; Hon Ming Yam; Zhongliang Guo; Chun Pong Lau
PRADA: Proactive Risk Assessment and Mitigation of Misinformed Demand Attacks on Navigational Route Recommendations. (8%)Ya-Ting Yang; Haozhe Lei; Quanyan Zhu
Evaluating Reliability in Medical DNNs: A Critical Analysis of Feature and Confidence-Based OOD Detection. (1%)Harry Anthony; Konstantinos Kamnitsas
2024-08-29
PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning. (92%)Noor Hussein; Fahad Shamshad; Muzammal Naseer; Karthik Nandakumar
STEREO: Towards Adversarially Robust Concept Erasing from Text-to-Image Generation Models. (83%)Koushik Srivatsan; Fahad Shamshad; Muzammal Naseer; Karthik Nandakumar
SFR-GNN: Simple and Fast Robust GNNs against Structural Attacks. (67%)Xing Ai; Guanyu Zhu; Yulin Zhu; Yu Zheng; Gaolei Li; Jianhua Li; Kai Zhou
Analyzing Inference Privacy Risks Through Gradients in Machine Learning. (54%)Zhuohang Li; Andrew Lowy; Jing Liu; Toshiaki Koike-Akino; Kieran Parsons; Bradley Malin; Ye Wang
Tex-ViT: A Generalizable, Robust, Texture-based dual-branch cross-attention deepfake detector. (12%)Deepak Dagar; Dinesh Kumar Vishwakarma
2024-08-28
Evaluating Model Robustness Using Adaptive Sparse L0 Regularization. (99%)Weiyou Liu; Zhenyang Li; Weitong Chen
Network transferability of adversarial patches in real-time object detection. (83%)Jens Bayer; Stefan Becker; David Münch; Michael Arens
Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks. (83%)Oscar Chew; Po-Yi Lu; Jayden Lin; Hsuan-Tien Lin
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation. (47%)Weilin Lin; Li Liu; Jianze Li; Hui Xiong
VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification. (2%)Yungi Cho; Woorim Han; Miseon Yu; Younghan Lee; Ho Bae; Yunheung Paek
FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks). (1%)Aman Priyanshu; Supriti Vijay
2024-08-27
Adversarial Attacks and Defenses in Multivariate Time-Series Forecasting for Smart and Connected Infrastructures. (99%)Pooja Krishan; Rohan Mohapatra; Saptarshi Sengupta
Certified Causal Defense with Generalizable Robustness. (99%)Yiran Qiao; Yu Yin; Chen Chen; Jing Ma
Improving Adversarial Robustness in Android Malware Detection by Reducing the Impact of Spurious Correlations. (99%)Hamid Bostani; Zhengyu Zhao; Veelasha Moonsamy
Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attack. (98%)Naufal Suryanto; Andro Aprila Adiputra; Ahmada Yusril Kadiptya; Yongsu Kim; Howon Kim
LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet. (12%)Nathaniel Li; Ziwen Han; Ian Steneker; Willow Primack; Riley Goodside; Hugh Zhang; Zifan Wang; Cristina Menghini; Summer Yue
Investigating Coverage Criteria in Large Language Models: An In-Depth Study Through Jailbreak Attacks. (11%)Shide Zhou; Tianlin Li; Kailong Wang; Yihao Huang; Ling Shi; Yang Liu; Haoyu Wang
Detecting AI Flaws: Target-Driven Attacks on Internal Faults in Language Models. (8%)Yuhao Du; Zhuo Li; Pengyu Cheng; Xiang Wan; Anningzhe Gao
SpecGuard: Specification Aware Recovery for Robotic Autonomous Vehicles from Physical Attacks. (3%)Pritam Dash; Ethan Chan; Karthik Pattabiraman
EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Models. (2%)Wenhan Yao; Zedong XingXiarun Chen; Jia Liu; yongqiang He; Weiping Wen
2024-08-26
TART: Boosting Clean Accuracy Through Tangent Direction Guided Adversarial Training. (99%)Bongsoo Yi; Rongjie Lai; Yao Li
2D-Malafide: Adversarial Attacks Against Face Deepfake Detection Systems. (99%)Chiara Galdi; Michele Panariello; Massimiliano Todisco; Nicholas Evans
Feedback-based Modal Mutual Search for Attacking Vision-Language Pre-training Models. (99%)Renhua Ding; Xinze Zhang; Xiao Yang; Kun He
Celtibero: Robust Layered Aggregation for Federated Learning. (92%)Borja Molina-Coronado
Dual Adversarial Perturbators Generate rich Views for Recommendation. (5%)Lijun Zhang; Yuan Yao; Haibo Ye
Investigating the Effectiveness of Bayesian Spam Filters in Detecting LLM-modified Spam Mails. (1%)Malte Josten; Torben Weis
Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models. (1%)Ian Stewart; Sameera Horawalavithana; Brendan Kennedy; Sai Munikoti; Karl Pazdernik
2024-08-25
On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective. (98%)Tal Alter; Raz Lapid; Moshe Sipper
RT-Attack: Jailbreaking Text-to-Image Models via Random Token. (97%)Sensen Gao; Xiaojun Jia; Yihao Huang; Ranjie Duan; Jindong Gu; Yang Liu; Qing Guo
TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models. (96%)Zelin Li; Kehai Chen; Lemao Liu; Xuefeng Bai; Mingming Yang; Yang Xiang; Min Zhang
Generalization of Graph Neural Networks is Robust to Model Mismatch. (1%)Zhiyang Wang; Juan Cervino; Alejandro Ribeiro
2024-08-24
Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach. (99%)Jiwei Guan; Tianyu Ding; Longbing Cao; Lei Pan; Chen Wang; Xi Zheng
Evaluating the Robustness of LiDAR-based 3D Obstacles Detection and Its Impacts on Autonomous Driving Systems. (1%)Tri Minh Triet Pham; Bo Yang; Jinqiu Yang
2024-08-23
Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks. (99%)Zhenyu Liu; Haoran Duan; Huizhi Liang; Yang Long; Vaclav Snasel; Guiseppe Nicosia; Rajiv Ranjan; Varun Ojha
Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples. (98%)Zhenyu Wang; John H. L. Hansen
Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting. (83%)Zhenyu Wang; Li Wan; Biqiao Zhang; Yiteng Huang; Shang-Wen Li; Ming Sun; Xin Lei; Zhaojun Yang
Protecting against simultaneous data poisoning attacks. (54%)Neel Alex; Shoaib Ahmed Siddiqui; Amartya Sanyal; David Krueger
2024-08-22
Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing. (99%)Zhibo Jin; Jiayu Zhang; Zhiyu Zhu; Yuchen Zhang; Jiahao Huang; Jianlong Zhou; Fang Chen
Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attacks. (99%)Zhibo Jin; Jiayu Zhang; Zhiyu Zhu; Xinyi Wang; Yiyun Huang; Huaming Chen
MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer. (98%)Ming Sun; Lihua Jing; Zixuan Zhu; Rui Wang
BankTweak: Adversarial Attack against Multi-Object Trackers by Manipulating Feature Banks. (80%)Woojin Shin; Donghwa Kang; Daejin Choi; Brent Kang; Jinkyu Lee; Hyeongboo Baek
On the Credibility of Backdoor Attacks Against Object Detectors in the Physical World. (75%)Bao Gia Doan; Dang Quang Nguyen; Callum Lindquist; Paul Montague; Tamas Abraham; Vel Olivier De; Seyit Camtepe; Salil S. Kanhere; Ehsan Abbasnejad; Damith C. Ranasinghe
Quantifying Psychological Sophistication of Malicious Emails. (2%)Theodore Longtchi; Rosana Montañez Rodriguez; Kora Gwartney; Ekzhin Ear; David P. Azari; Christopher P. Kelley; Shouhuai Xu
Is Generative AI the Next Tactical Cyber Weapon For Threat Actors? Unforeseen Implications of AI Generated Cyber Attacks. (2%)Yusuf Usman; Aadesh Upadhyay; Prashnna Gyawali; Robin Chataut
VALE: A Multimodal Visual and Language Explanation Framework for Image Classifiers using eXplainable AI and Language Models. (2%)Purushothaman Natarajan; Athira Nambiar
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models. (2%)Yige Li; Hanxun Huang; Yunhan Zhao; Xingjun Ma; Jun Sun
2024-08-21
Query-Efficient Video Adversarial Attack with Stylized Logo. (99%)Duoxun Tang; Yuxin Cao; Xi Xiao; Derui Wang; Sheng Wen; Tianqing Zhu
Pixel Is Not A Barrier: An Effective Evasion Attack for Pixel-Domain Diffusion Models. (74%)Chun-Yen Shih; Li-Xuan Peng; Jia-Wei Liao; Ernie Chu; Cheng-Fu Chou; Jun-Cheng Chen
A Practical Trigger-Free Backdoor Attack on Neural Networks. (67%)Jiahao Wang; Xianglong Zhang; Xiuzhen Cheng; Pengfei Hu; Guoming Zhang
First line of defense: A robust first layer mitigates adversarial attacks. (54%)Janani Suresh; Nancy Nayak; Sheetal Kalyani
Exploring Robustness of Visual State Space model against Backdoor Attacks. (45%)Cheng-Yi Lee; Cheng-Chang Tsai; Chia-Mu Yu; Chun-Shien Lu
Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks. (26%)Yiyi Chen; Russa Biswas; Heather Lent; Johannes Bjerva
Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets Protection. (12%)Jingwei Sun; Xuchong Zhang; Changfeng Sun; Qicheng Bai; Hongbin Sun
Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks. (10%)Ziqiang Li; Yueqi Zeng; Pengfei Xia; Lei Liu; Zhangjie Fu; Bin Li
2024-08-20
GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization. (99%)Xiaodong Yang; Xiaoting Li; Huiyuan Chen; Yiwei Cai
Correlation Analysis of Adversarial Attack in Time Series Classification. (99%)Zhengyang Li; Wenhao Liang; Chang Dong; Weitong Chen; Dong Huang
Privacy-preserving Universal Adversarial Defense for Black-box Models. (99%)Qiao Li; Cong Wu; Jing Chen; Zijun Zhang; Kun He; Ruiying Du; Xinxin Wang; Qingchuang Zhao; Yang Liu
MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification. (99%)Huafeng Qin; Yuming Fu; Huiyan Zhang; Mounim A. El-Yacoubi; Xinbo Gao; Qun Song; Jun Wang
Revisiting Min-Max Optimization Problem in Adversarial Training. (97%)Sina Hajer Ahmadi; Hassan Bahrami
Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models. (97%)Cong Wan; Yuhang He; Xiang Song; Yihong Gong
Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification. (87%)Hanrui Wang; Ruoxi Sun; Cunjian Chen; Minhui Xue; Lay-Ki Soon; Shuo Wang; Zhe Jin
Adversarial Attack for Explanation Robustness of Rationalization Models. (82%)Yuankai Zhang; Lingxiao Kong; Haozhao Wang; Ruixuan Li; Jun Wang; Yuhua Li; Wei Liu
Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models. (73%)Hongbang Yuan; Zhuoran Jin; Pengfei Cao; Yubo Chen; Kang Liu; Jun Zhao
A Grey-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse. (68%)Zhongliang Guo; Lei Fang; Jingyu Lin; Yifei Qian; Shuai Zhao; Zeyu Wang; Junhao Dong; Cunjian Chen; Ognjen Arandjelović; Chun Pong Lau
Security Assessment of Hierarchical Federated Deep Learning. (67%)D Alqattan; R Sun; H Liang; G Nicosia; V Snasel; R Ranjan; V Ojha
Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks. (54%)Saleh Sargolzaei; Luis Rueda
Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique. (50%)Tej Deep Pala; Vernon Y. H. Toh; Rishabh Bhardwaj; Soujanya Poria
Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priors. (33%)Fahad Shamshad; Muzammal Naseer; Karthik Nandakumar
EEG-Defender: Defending against Jailbreak through Early Exit Generation of Large Language Models. (31%)Chongwen Zhao; Zhihao Dou; Kaizhu Huang
Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender Systems. (26%)Yunfan Wu; Qi Cao; Shuchang Tao; Kaike Zhang; Fei Sun; Huawei Shen
Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer. (10%)Weipeng Jiang; Zhenting Wang; Juan Zhai; Shiqing Ma; Zhengyu Zhao; Chao Shen
Security Attacks on LLM-based Code Completion Tools. (8%)Wen Cheng; Ke Sun; Xinyu Zhang; Wei Wang
MEGen: Generative Backdoor in Large Language Models via Model Editing. (2%)Jiyang Qiu; Xinbei Ma; Zhuosheng Zhang; Hai Zhao
Learning Randomized Algorithms with Transformers. (1%)Oswald Johannes von; Seijin Kobayashi; Yassir Akram; Angelika Steger
2024-08-19
Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks. (99%)Hetvi Waghela; Jaydip Sen; Sneha Rakshit
Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis. (99%)Kira Maag; Roman Resner; Asja Fischer
Segment-Anything Models Achieve Zero-shot Robustness in Autonomous Driving. (98%)Jun Yan; Pengyu Wang; Danni Wang; Weiquan Huang; Daniel Watzenig; Huilin Yin
Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency. (31%)Bhavna Gopal; Huanrui Yang; Jingyang Zhang; Mark Horton; Yiran Chen
The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks. (5%)Niyar R Barman; Krish Sharma; Ashhar Aziz; Shashwat Bajpai; Shwetangshu Biswas; Vasu Sharma; Vinija Jain; Aman Chadha; Amit Sheth; Amitava Das
Transferring Backdoors between Large Language Models by Knowledge Distillation. (2%)Pengzhou Cheng; Zongru Wu; Tianjie Ju; Wei Du; Zhuosheng Zhang Gongshen Liu
Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting. (1%)Yun-Da Tsai; Ting-Yu Yen; Keng-Te Liao; Shou-De Lin
Perfectly Undetectable Reflection and Scaling False Data Injection Attacks via Affine Transformation on Mobile Robot Trajectory Tracking Control. (1%)Jun Ueda; Hyukbin Kwon
2024-08-18
Enhancing Adversarial Transferability with Adversarial Weight Tuning. (99%)Jiahao Chen; Zhou Feng; Rui Zeng; Yuwen Pu; Chunyi Zhou; Yi Jiang; Yuyou Gan; Jinbao Li; Shouling Ji; Shouling_Ji
Regularization for Adversarial Robust Learning. (41%)Jie Wang; Rui Gao; Yao Xie
Adversarial Attacked Teacher for Unsupervised Domain Adaptive Object Detection. (31%)Kaiwen Wang; Yinzhe Shen; Martin Lauer
GANPrompt: Enhancing Robustness in LLM-Based Recommendations with GAN-Enhanced Diversity Prompts. (1%)Xinyu Li; Chuang Zhao; Hongke Zhao; Likang Wu; Ming HE
Global BGP Attacks that Evade Route Monitoring. (1%)Henry Birge-Lee; Maria Apostolaki; Jennifer Rexford
2024-08-17
Attack Anything: Blind DNNs via Universal Background Adversarial Attack. (99%)Jiawei Lian; Shaohui Mei; Xiaofei Wang; Yi Wang; Lefan Wang; Yingjie Lu; Mingyang Ma; Lap-Pui Chau
Training Verifiably Robust Agents Using Set-Based Reinforcement Learning. (75%)Manuel Wendl; Lukas Koller; Tobias Ladner; Matthias Althoff
DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization. (67%)Pucheng Dang; Xing Hu; Dong Li; Rui Zhang; Qi Guo; Kaidi Xu
PADetBench: Towards Benchmarking Physical Attacks against Object Detection. (62%)Jiawei Lian; Jianhong Pan; Lefan Wang; Yi Wang; Lap-Pui Chau; Shaohui Mei
Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model. (31%)Massimiliano Todisco; Michele Panariello; Xin Wang; Héctor Delgado; Kong Aik Lee; Nicholas Evans
BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger. (10%)Yulin Chen; Haoran Li; Zihao Zheng; Yangqiu Song
Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks. (5%)Kexin Chen; Yi Liu; Dongxia Wang; Jiaying Chen; Wenhai Wang
PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks. (2%)Xiyue Zhang; Benjie Wang; Marta Kwiatkowska; Huan Zhang
Out-of-distribution materials property prediction using adversarial learning based fine-tuning. (1%)Qinyang Li; Nicholas Miklaucic; Jianjun Hu
2024-08-16
Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models. (98%)Qingyuan Zeng; Zhenzhong Wang; Yiu-ming Cheung; Min Jiang
Towards Physical World Backdoor Attacks against Skeleton Action Recognition. (93%)Qichen Zheng; Yi Yu; Siyuan Yang; Jun Liu; Kwok-Yan Lam; Alex Kot
LEVIS: Large Exact Verifiable Input Spaces for Neural Networks. (87%)Mohamad Fares El Hajj Chehade; Brian Wesley Bell; Russell Bent; Hao Zhu; Wenting Li
Visual-Friendly Concept Protection via Selective Adversarial Perturbations. (75%)Xiaoyue Mi; Fan Tang; Juan Cao; Peng Li; Yang Liu
Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks? (75%)Zhongjian Zhang; Xiao Wang; Huichi Zhou; Yue Yu; Mengmei Zhang; Cheng Yang; Chuan Shi
Mitigating Backdoor Attacks in Federated Learning via Flipping Weight Updates of Low-Activation Input Neurons. (1%)Binbin Ding; Penghui Yang; Zeqing Ge; Shengjun Huang
2024-08-15
DFT-Based Adversarial Attack Detection in MRI Brain Imaging: Enhancing Diagnostic Accuracy in Alzheimer's Case Studies. (99%)Mohammad Hossein Najafi; Mohammad Morsali; Mohammadmahdi Vahediahmar; Saeed Bagheri Shouraki
A Multi-task Adversarial Attack Against Face Authentication. (98%)Hanrui Wang; Shuo Wang; Cunjian Chen; Massimo Tistarelli; Zhe Jin
Evaluating Text Classification Robustness to Part-of-Speech Adversarial Examples. (98%)Anahita Samadi; Allison Sullivan
Unlearnable Examples Detection via Iterative Filtering. (88%)Yi Yu; Qichen Zheng; Siyuan Yang; Wenhan Yang; Jun Liu; Shijian Lu; Yap-Peng Tan; Kwok-Yan Lam; Alex Kot
A Survey of Trojan Attacks and Defenses to Deep Neural Networks. (78%)Lingxin Jin; Xianyu Wen; Wei Jiang; Jinyu Zhan
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness. (76%)Hefei Mei; Minjing Dong; Chang Xu
Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks. (74%)Jiawei Zhao; Kejiang Chen; Xiaojian Yuan; Weiming Zhang
$\textit{MMJ-Bench}$: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models. (70%)Fenghua Weng; Yue Xu; Chengyan Fu; Wenjie Wang
Random Gradient Masking as a Defensive Measure to Deep Leakage in Federated Learning. (8%)Joon Kim; Sejin Park
A Robust Multi-Stage Intrusion Detection System for In-Vehicle Network Security using Hierarchical Federated Learning. (2%)Muzun Althunayyan; Amir Javed; Omer Rana
2024-08-14
Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack. (99%)Zhibo Jin; Jiayu Zhang; Zhiyu Zhu; Chenyu Zhang; Jiahao Huang; Jianlong Zhou; Fang Chen
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases. (98%)Thibault Simonetto; Salah Ghamizi; Maxime Cordy
Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation. (80%)Ricky Maulana Fajri; Yulong Pei; Lu Yin; Mykola Pechenizkiy
Achieving Data Efficient Neural Networks with Hybrid Concept-based Models. (70%)Tobias A. Opsahl; Vegard Antun
Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms. (67%)Francesco Villani; Dario Lazzaro; Antonio Emanuele Cinà; Matteo Dell'Amico; Battista Biggio; Fabio Roli
BadMerging: Backdoor Attacks Against Model Merging. (47%)Jinghuai Zhang; Jianfeng Chi; Zheng Li; Kunlin Cai; Yang Zhang; Yuan Tian
BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning. (38%)Asif Hanif; Fahad Shamshad; Muhammad Awais; Muzammal Naseer; Fahad Shahbaz Khan; Karthik Nandakumar; Salman Khan; Rao Muhammad Anwer
Cognitive Networks and Performance Drive fMRI-Based State Classification Using DNN Models. (1%)Murat Kucukosmanoglu; Javier O. Garcia; Justin Brooks; Kanika Bansal
2024-08-13
DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World. (92%)Jikang Cheng; Ying Zhang; Zhongyuan Wang; Zou Qin; Chen Li
Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage. (12%)Aishwarya Gupta; Indranil Saha; Piyush Rai
Imagen 3. (10%)Imagen-Team-Google; :; Jason Baldridge; Jakob Bauer; Mukul Bhutani; Nicole Brichtova; Andrew Bunner; Kelvin Chan; Yichang Chen; Sander Dieleman; Yuqing Du; Zach Eaton-Rosen; Hongliang Fei; Freitas Nando de; Yilin Gao; Evgeny Gladchenko; Sergio Gómez Colmenarejo; Mandy Guo; Alex Haig; Will Hawkins; Hexiang Hu; Huilian Huang; Tobenna Peter Igwe; Christos Kaplanis; Siavash Khodadadeh; Yelin Kim; Ksenia Konyushkova; Karol Langner; Eric Lau; Shixin Luo; Soňa Mokrá; Henna Nandwani; Yasumasa Onoe; Aäron van den Oord; Zarana Parekh; Jordi Pont-Tuset; Hang Qi; Rui Qian; Deepak Ramachandran; Poorva Rane; Abdullah Rashwan; Ali Razavi; Robert Riachi; Hansa Srinivasan; Srivatsan Srinivasan; Robin Strudel; Benigno Uria; Oliver Wang; Su Wang; Austin Waters; Chris Wolff; Auriel Wright; Zhisheng Xiao; Hao Xiong; Keyang Xu; Zee Marc van; Junlin Zhang; Katie Zhang; Wenlei Zhou; Konrad Zolna; Ola Aboubakar; Canfer Akbulut; Oscar Akerlund; Isabela Albuquerque; Nina Anderson; Marco Andreetto; Lora Aroyo; Ben Bariach; David Barker; Sherry Ben; Dana Berman; Courtney Biles; Irina Blok; Pankil Botadra; Jenny Brennan; Karla Brown; John Buckley; Rudy Bunel; Elie Bursztein; Christina Butterfield; Ben Caine; Viral Carpenter; Norman Casagrande; Ming-Wei Chang; Solomon Chang; Shamik Chaudhuri; Tony Chen; John Choi; Dmitry Churbanau; Nathan Clement; Matan Cohen; Forrester Cole; Mikhail Dektiarev; Vincent Du; Praneet Dutta; Tom Eccles; Ndidi Elue; Ashley Feden; Shlomi Fruchter; Frankie Garcia; Roopal Garg; Weina Ge; Ahmed Ghazy; Bryant Gipson; Andrew Goodman; Dawid Górny; Sven Gowal; Khyatti Gupta; Yoni Halpern; Yena Han; Susan Hao; Jamie Hayes; Amir Hertz; Ed Hirst; Tingbo Hou; Heidi Howard; Mohamed Ibrahim; Dirichi Ike-Njoku; Joana Iljazi; Vlad Ionescu; William Isaac; Reena Jana; Gemma Jennings; Donovon Jenson; Xuhui Jia; Kerry Jones; Xiaoen Ju; Ivana Kajic; Christos Kaplanis; Burcu Karagol Ayan; Jacob Kelly; Suraj Kothawade; Christina Kouridi; Ira Ktena; Jolanda Kumakaw; Dana Kurniawan; Dmitry Lagun; Lily Lavitas; Jason Lee; Tao Li; Marco Liang; Maggie Li-Calis; Yuchi Liu; Javier Lopez Alberca; Peggy Lu; Kristian Lum; Yukun Ma; Chase Malik; John Mellor; Inbar Mosseri; Tom Murray; Aida Nematzadeh; Paul Nicholas; João Gabriel Oliveira; Guillermo Ortiz-Jimenez; Michela Paganini; Tom Le Paine; Roni Paiss; Alicia Parrish; Anne Peckham; Vikas Peswani; Igor Petrovski; Tobias Pfaff; Alex Pirozhenko; Ryan Poplin; Utsav Prabhu; Yuan Qi; Matthew Rahtz; Cyrus Rashtchian; Charvi Rastogi; Amit Raul; Ali Razavi; Sylvestre-Alvise Rebuffi; Susanna Ricco; Felix Riedel; Dirk Robinson; Pankaj Rohatgi; Bill Rosgen; Sarah Rumbley; Moonkyung Ryu; Anthony Salgado; Sahil Singla; Florian Schroff; Candice Schumann; Tanmay Shah; Brendan Shillingford; Kaushik Shivakumar; Dennis Shtatnov; Zach Singer; Evgeny Sluzhaev; Valerii Sokolov; Thibault Sottiaux; Florian Stimberg; Brad Stone; David Stutz; Yu-Chuan Su; Eric Tabellion; Shuai Tang; David Tao; Kurt Thomas; Gregory Thornton; Andeep Toor; Cristian Udrescu; Aayush Upadhyay; Cristina Vasconcelos; Alex Vasiloff; Andrey Voynov; Amanda Walker; Luyu Wang; Miaosen Wang; Simon Wang; Stanley Wang; Qifei Wang; Yuxiao Wang; Ágoston Weisz; Olivia Wiles; Chenxia Wu; Xingyu Federico Xu; Andrew Xue; Jianbo Yang; Luo Yu; Mete Yurtoglu; Ali Zand; Han Zhang; Jiageng Zhang; Catherine Zhao; Adilet Zhaxybay; Miao Zhou; Shengqi Zhu; Zhenkai Zhu; Dawn Bloxwich; Mahyar Bordbar; Luis C. Cobo; Eli Collins; Shengyang Dai; Tulsee Doshi; Anca Dragan; Douglas Eck; Demis Hassabis; Sissie Hsiao; Tom Hume; Koray Kavukcuoglu; Helen King; Jack Krawczyk; Yeqing Li; Kathy Meier-Hellstern; Andras Orban; Yury Pinsky; Amar Subramanya; Oriol Vinyals; Ting Yu; Yori Zwols
2024-08-12
Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment. (99%)Kejia Zhang; Juanjuan Weng; Zhiming Luo; Shaozi Li
Fooling SHAP with Output Shuffling Attacks. (81%)Jun Yuan; Aritra Dasgupta
Understanding Byzantine Robustness in Federated Learning with A Black-box Server. (13%)Fangyuan Zhao; Yuexiang Xie; Xuebin Ren; Bolin Ding; Shusen Yang; Yaliang Li
2024-08-11
Improving Adversarial Transferability with Neighbourhood Gradient Information. (99%)Haijing Guo; Jiafeng Wang; Zhaoyu Chen; Kaixun Jiang; Lingyi Hong; Pinxue Guo; Jinglun Li; Wenqiang Zhang
Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information. (98%)Mingkun Zhang; Jianing Li; Wei Chen; Jiafeng Guo; Xueqi Cheng
Kov: Transferable and Naturalistic Black-Box LLM Attacks using Markov Decision Processes and Tree Search. (9%)Robert J. Moss
2024-08-10
ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack. (99%)Ziyi Gao; Kai Chen; Zhipeng Wei; Tingshu Mou; Jingjing Chen; Zhiyu Tan; Hao Li; Yu-Gang Jiang
StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model. (99%)Ziyin Zhou; Ke Sun; Zhongxi Chen; Huafeng Kuang; Xiaoshuai Sun; Rongrong Ji
PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark. (13%)Cheng Wei; Yang Wang; Kuofeng Gao; Shuo Shao; Yiming Li; Zhibo Wang; Zhan Qin
2024-08-09
Modeling Electromagnetic Signal Injection Attacks on Camera-based Smart Systems: Applications and Mitigation. (84%)Youqian Zhang; Michael Cheung; Chunxi Yang; Xinwei Zhai; Zitong Shen; Xinyu Ji; Eugene Y. Fu; Sze-Yiu Chau; Xiapu Luo
A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares. (2%)Stav Cohen; Ron Bitton; Ben Nassi
Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks. (2%)Stefano Gianluca De; Lea Schönherr; Giancarlo Pellegrino
TrajFM: A Vehicle Trajectory Foundation Model for Region and Task Transferability. (1%)Yan Lin; Tonglong Wei; Zeyu Zhou; Haomin Wen; Jilin Hu; Shengnan Guo; Youfang Lin; Huaiyu Wan
2024-08-08
Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit. (99%)Duanyi Yao; Songze Li; Ye Xue; Jin Liu
Adversarially Robust Industrial Anomaly Detection Through Diffusion Model. (99%)Yuanpu Cao; Lu Lin; Jinghui Chen
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness. (99%)Stanislav Fort; Balaji Lakshminarayanan
Eliminating Backdoors in Neural Code Models via Trigger Inversion. (92%)Weisong Sun; Yuchen Chen; Chunrong Fang; Yebo Feng; Yuan Xiao; An Guo; Quanjun Zhang; Yang Liu; Baowen Xu; Zhenyu Chen
Improving Network Interpretability via Explanation Consistency Evaluation. (81%)Hefeng Wu; Hao Jiang; Keze Wang; Ziyi Tang; Xianghuan He; Liang Lin
Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hiding. (80%)Jonggyu Jang; Hyeonsu Lyu; Seongjin Hwang; Hyun Jong Yang
Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness. (67%)Xiaojing Fan; Chunliang Tao
Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNs. (61%)Soutrik Roy Chowdhury
h4rm3l: A Dynamic Benchmark of Composable Jailbreak Attacks for LLM Safety Assessment. (15%)Moussa Koulako Bala Doumbouya; Ananjan Nandi; Gabriel Poesia; Davide Ghilardi; Anna Goldie; Federico Bianchi; Dan Jurafsky; Christopher D. Manning
VideoQA in the Era of LLMs: An Empirical Study. (1%)Junbin Xiao; Nanxin Huang; Hangyu Qin; Dongyang Li; Yicong Li; Fengbin Zhu; Zhulin Tao; Jianxing Yu; Liang Lin; Tat-Seng Chua; Angela Yao
2024-08-07
Investigating Adversarial Attacks in Software Analytics via Machine Learning Explainability. (99%)MD Abdul Awal; Mrigank Rochan; Chanchal K. Roy
Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks. (98%)Keiichiro Yamamura; Issa Oe; Hiroki Ishikura; Katsuki Fujisawa
EdgeShield: A Universal and Efficient Edge Computing Framework for Robust AI. (83%)Duo Zhong; Bojing Li; Xiang Chen; Chenchen Liu
EnJa: Ensemble Jailbreak on Large Language Models. (83%)Jiahao Zhang; Zilong Wang; Ruofan Wang; Xingjun Ma; Yu-Gang Jiang
MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems. (76%)Renzhi Wang; Zhehua Zhou; Jiayang Song; Xuan Xie; Xiaofei Xie; Lei Ma
LaFA: Latent Feature Attacks on Non-negative Matrix Factorization. (38%)Minh Vu; Ben Nebgen; Erik Skau; Geigh Zollicoffer; Juan Castorena; Kim Rasmussen; Boian Alexandrov; Manish Bhattarai
MTDSense: AI-Based Fingerprinting of Moving Target Defense Techniques in Software-Defined Networking. (26%)Tina Moghaddam; Guowei Yang; Chandra Thapa; Seyit Camtepe; Dan Dongseong Kim
FDI: Attack Neural Code Generation Systems through User Feedback Channel. (5%)Zhensu Sun; Xiaoning Du; Xiapu Luo; Fu Song; David Lo; Li Li
Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation. (1%)Guy Amir; Shahaf Bassan; Guy Katz
Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models. (1%)Shachi H Kumar; Saurav Sahay; Sahisnu Mazumder; Eda Okur; Ramesh Manuvinakurike; Nicole Beckage; Hsuan Su; Hung-yi Lee; Lama Nachman
2024-08-06
Adversarial Robustness of Open-source Text Classification Models and Fine-Tuning Chains. (98%)Hao Qin; Mingyang Li; Junjie Wang; Qing Wang
Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models. (98%)Haonan Zheng; Wen Jiang; Xinyang Deng; Wenrui Li
Simple Perturbations Subvert Ethereum Phishing Transactions Detection: An Empirical Analysis. (92%)Ahod Alghureid; David Mohaisen
Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey. (64%)Vu Tuan Truong; Luan Ba Dang; Long Bao Le
A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems. (2%)Wenxiao Zhang; Xiangrui Kong; Conan Dewitt; Thomas Braunl; Jin B. Hong
2024-08-05
On the Robustness of Malware Detectors to Adversarial Samples. (99%)Muhammad Salman; Benjamin Zi Hao Zhao; Hassan Jameel Asghar; Muhammad Ikram; Sidharth Kaushik; Mohamed Ali Kaafar
Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense. (84%)Qilei Li; Ahmed M. Abdelmoniem
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models. (26%)Muxi Diao; Rumei Li; Shiyang Liu; Guogang Liao; Jingang Wang; Xunliang Cai; Weiran Xu
Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models. (13%)Zi Liang; Haibo Hu; Qingqing Ye; Yaxin Xiao; Haoyang Li
Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services. (13%)Shaopeng Fu; Xuexue Sun; Ke Qing; Tianhang Zheng; Di Wang
Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models? (8%)Mohammad Bahrami Karkevandi; Nishant Vishwamitra; Peyman Najafirad
RCDM: Enabling Robustness for Conditional Diffusion Model. (4%)Weifeng Xu; Xiang Zhu; Xiaoyong Li
Compromising Embodied Agents with Contextual Backdoor Attacks. (4%)Aishan Liu; Yuguang Zhou; Xianglong Liu; Tianyuan Zhang; Siyuan Liang; Jiakai Wang; Yanjun Pu; Tianlin Li; Junqi Zhang; Wenbo Zhou; Qing Guo; Dacheng Tao
Practical Attacks against Black-box Code Completion Engines. (4%)Slobodan Jenko; Jingxuan He; Niels Mündler; Mark Vero; Martin Vechev
2024-08-04
A Survey and Evaluation of Adversarial Attacks for Object Detection. (99%)Khoi Nguyen Tiet Nguyen; Wenyu Zhang; Kangkang Lu; Yuhuan Wu; Xingjian Zheng; Hui Li Tan; Liangli Zhen
AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning. (99%)Xin Wang; Kai Chen; Xingjun Ma; Zhineng Chen; Jingjing Chen; Yu-Gang Jiang
Label Augmentation for Neural Networks Robustness. (98%)Fatemeh Amerehi; Patrick Healy
Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification. (76%)Honglin Gao; Gaoxi Xiao
Model Hijacking Attack in Federated Learning. (75%)Zheng Li; Siyuan Wu; Ruichuan Chen; Paarijaat Aditya; Istemi Ekin Akkus; Manohar Vanga; Min Zhang; Hao Li; Yang Zhang
Robustness of Watermarking on Text-to-Image Diffusion Models. (22%)Xiaodong Wu; Xiangman Li; Jianbing Ni
FovEx: Human-inspired Explanations for Vision Transformers and Convolutional Neural Networks. (1%)Mahadev Prasad Panda; Matteo Tiezzi; Martina Vilas; Gemma Roig; Bjoern M. Eskofier; Dario Zanca
2024-08-03
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features. (99%)Peng Cheng; Yuwei Wang; Peng Huang; Zhongjie Ba; Xiaodong Lin; Feng Lin; Li Lu; Kui Ren
Joint Universal Adversarial Perturbations with Interpretations. (99%)Liang-bo Ning; Zeyu Dai; Wenqi Fan; Jingran Su; Chao Pan; Luning Wang; Qing Li
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers. (99%)Weijie Zheng; Xingjun Ma; Hanxun Huang; Zuxuan Wu; Yu-Gang Jiang
2024-08-02
Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics. (98%)Alexander Gushchin; Khaled Abud; Georgii Bychkov; Ekaterina Shumitskaya; Anna Chistyakova; Sergey Lavrushkin; Bader Rasheed; Kirill Malyshev; Dmitriy Vatolin; Anastasia Antsiferova
Trustworthy Machine Learning under Social and Adversarial Data Sources. (83%)Han Shao
EmoBack: Backdoor Attacks Against Speaker Identification Using Emotional Prosody. (80%)Coen Schoof; Stefanos Koffas; Mauro Conti; Stjepan Picek
Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition. (61%)Róisín Luo; James McDermott; Colm O'Riordan
Assessing Robustness of Machine Learning Models using Covariate Perturbations. (33%)Arun Prakash R; Anwesha Bhattacharyya; Joel Vaughan; Vijayan N. Nair
Certifiably Robust Encoding Schemes. (31%)Aman Saxena; Tom Wollschläger; Nicola Franco; Jeanette Miriam Lorenz; Stephan Günnemann
Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs. (2%)Peng Ding; Jingyu Wu; Jun Kuang; Dan Ma; Xuezhi Cao; Xunliang Cai; Shi Chen; Jiajun Chen; Shujian Huang
2024-08-01
Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion. (99%)Honglei Miao; Fan Ma; Ruijie Quan; Kun Zhan; Yi Yang
OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack. (99%)Kuo Gai; Sicong Wang; Shihua Zhang
Securing the Diagnosis of Medical Imaging: An In-depth Analysis of AI-Resistant Attacks. (99%)Angona Biswas; MD Abdullah Al Nasim; Kishor Datta Gupta; Roy George; Abdur Rashid
CERT-ED: Certifiably Robust Text Classification for Edit Distance. (98%)Zhuoqun Huang; Neil G Marchant; Olga Ohrimenko; Benjamin I. P. Rubinstein
ADBM: Adversarial diffusion bridge model for reliable adversarial purification. (96%)Xiao Li; Wenxuan Sun; Huanran Chen; Qiongxiu Li; Yining Liu; Yingzhe He; Jie Shi; Xiaolin Hu
Discrete Randomized Smoothing Meets Quantum Computing. (41%)Tom Wollschläger; Aman Saxena; Nicola Franco; Jeanette Miriam Lorenz; Stephan Günnemann
Adversarial Text Rewriting for Text-aware Recommender Systems. (13%)Sejoon Oh; Gaurav Verma; Srijan Kumar
MAARS: Multi-Rate Attack-Aware Randomized Scheduling for Securing Real-time Systems. (1%)Arkaprava Sain; Sunandan Adhikary; Ipsita Koley; Soumyajit Dey
Pathway to Secure and Trustworthy 6G for LLMs: Attacks, Defense, and Opportunities. (1%)Sunder Ali Khowaja; Parus Khuwaja; Kapal Dev; Hussam Al Hamadi; Engin Zeydan
2024-07-31
Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models. (98%)Yue Xu; Xiuyuan Qi; Zhan Qin; Wenjie Wang
On the Perturbed States for Transformed Input-robust Reinforcement Learning. (92%)Tung M. Luu; Haeyong Kang; Tri Ton; Thanh Nguyen; Chang D. Yoo
The Llama 3 Herd of Models. (62%)Abhimanyu Jack Dubey; Abhinav Jack Jauhri; Abhinav Jack Pandey; Abhishek Jack Kadian; Ahmad Jack Al-Dahle; Aiesha Jack Letman; Akhil Jack Mathur; Alan Jack Schelten; Amy Jack Yang; Angela Jack Fan; Anirudh Jack Goyal; Anthony Jack Hartshorn; Aobo Jack Yang; Archi Jack Mitra; Archie Jack Sravankumar; Artem Jack Korenev; Arthur Jack Hinsvark; Arun Jack Rao; Aston Jack Zhang; Aurelien Jack Rodriguez; Austen Jack Gregerson; Ava Jack Spataru; Baptiste Jack Roziere; Bethany Jack Biron; Binh Jack Tang; Bobbie Jack Chern; Charlotte Jack Caucheteux; Chaya Jack Nayak; Chloe Jack Bi; Chris Jack Marra; Chris Jack McConnell; Christian Jack Keller; Christophe Jack Touret; Chunyang Jack Wu; Corinne Jack Wong; Cristian Canton Jack Ferrer; Cyrus Jack Nikolaidis; Damien Jack Allonsius; Daniel Jack Song; Danielle Jack Pintz; Danny Jack Livshits; David Jack Esiobu; Dhruv Jack Choudhary; Dhruv Jack Mahajan; Diego Jack Garcia-Olano; Diego Jack Perino; Dieuwke Jack Hupkes; Egor Jack Lakomkin; Ehab Jack AlBadawy; Elina Jack Lobanova; Emily Jack Dinan; Eric Michael Jack Smith; Filip Jack Radenovic; Frank Jack Zhang; Gabriel Jack Synnaeve; Gabrielle Jack Lee; Georgia Lewis Jack Anderson; Graeme Jack Nail; Gregoire Jack Mialon; Guan Jack Pang; Guillem Jack Cucurell; Hailey Jack Nguyen; Hannah Jack Korevaar; Hu Jack Xu; Hugo Jack Touvron; Iliyan Jack Zarov; Imanol Arrieta Jack Ibarra; Isabel Jack Kloumann; Ishan Jack Misra; Ivan Jack Evtimov; Jade Jack Copet; Jaewon Jack Lee; Jan Jack Geffert; Jana Jack Vranes; Jason Jack Park; Jay Jack Mahadeokar; Jeet Jack Shah; der Linde Jelmer Jack van; Jennifer Jack Billock; Jenny Jack Hong; Jenya Jack Lee; Jeremy Jack Fu; Jianfeng Jack Chi; Jianyu Jack Huang; Jiawen Jack Liu; Jie Jack Wang; Jiecao Jack Yu; Joanna Jack Bitton; Joe Jack Spisak; Jongsoo Jack Park; Joseph Jack Rocca; Joshua Jack Johnstun; Joshua Jack Saxe; Junteng Jack Jia; Kalyan Vasuden Jack Alwala; Kartikeya Jack Upasani; Kate Jack Plawiak; Ke Jack Li; Kenneth Jack Heafield; Kevin Jack Stone; Khalid Jack El-Arini; Krithika Jack Iyer; Kshitiz Jack Malik; Kuenley Jack Chiu; Kunal Jack Bhalla; Lauren Jack Rantala-Yeary; der Maaten Laurens Jack van; Lawrence Jack Chen; Liang Jack Tan; Liz Jack Jenkins; Louis Jack Martin; Lovish Jack Madaan; Lubo Jack Malo; Lukas Jack Blecher; Lukas Jack Landzaat; Oliveira Luke Jack de; Madeline Jack Muzzi; Mahesh Jack Pasupuleti; Mannat Jack Singh; Manohar Jack Paluri; Marcin Jack Kardas; Mathew Jack Oldham; Mathieu Jack Rita; Maya Jack Pavlova; Melanie Jack Kambadur; Mike Jack Lewis; Min Jack Si; Mitesh Kumar Jack Singh; Mona Jack Hassan; Naman Jack Goyal; Narjes Jack Torabi; Nikolay Jack Bashlykov; Nikolay Jack Bogoychev; Niladri Jack Chatterji; Olivier Jack Duchenne; Onur Jack Çelebi; Patrick Jack Alrassy; Pengchuan Jack Zhang; Pengwei Jack Li; Petar Jack Vasic; Peter Jack Weng; Prajjwal Jack Bhargava; Pratik Jack Dubal; Praveen Jack Krishnan; Punit Singh Jack Koura; Puxin Jack Xu; Qing Jack He; Qingxiao Jack Dong; Ragavan Jack Srinivasan; Raj Jack Ganapathy; Ramon Jack Calderer; Ricardo Silveira Jack Cabral; Robert Jack Stojnic; Roberta Jack Raileanu; Rohit Jack Girdhar; Rohit Jack Patel; Romain Jack Sauvestre; Ronnie Jack Polidoro; Roshan Jack Sumbaly; Ross Jack Taylor; Ruan Jack Silva; Rui Jack Hou; Rui Jack Wang; Saghar Jack Hosseini; Sahana Jack Chennabasappa; Sanjay Jack Singh; Sean Jack Bell; Seohyun Sonia Jack Kim; Sergey Jack Edunov; Shaoliang Jack Nie; Sharan Jack Narang; Sharath Jack Raparthy; Sheng Jack Shen; Shengye Jack Wan; Shruti Jack Bhosale; Shun Jack Zhang; Simon Jack Vandenhende; Soumya Jack Batra; Spencer Jack Whitman; Sten Jack Sootla; Stephane Jack Collot; Suchin Jack Gururangan; Sydney Jack Borodinsky; Tamar Jack Herman; Tara Jack Fowler; Tarek Jack Sheasha; Thomas Jack Georgiou; Thomas Jack Scialom; Tobias Jack Speckbacher; Todor Jack Mihaylov; Tong Jack Xiao; Ujjwal Jack Karn; Vedanuj Jack Goswami; Vibhor Jack Gupta; Vignesh Jack Ramanathan; Viktor Jack Kerkez; Vincent Jack Gonguet; Virginie Jack Do; Vish Jack Vogeti; Vladan Jack Petrovic; Weiwei Jack Chu; Wenhan Jack Xiong; Wenyin Jack Fu; Whitney Jack Meers; Xavier Jack Martinet; Xiaodong Jack Wang; Xiaoqing Ellen Jack Tan; Xinfeng Jack Xie; Xuchao Jack Jia; Xuewei Jack Wang; Yaelle Jack Goldschlag; Yashesh Jack Gaur; Yasmine Jack Babaei; Yi Jack Wen; Yiwen Jack Song; Yuchen Jack Zhang; Yue Jack Li; Yuning Jack Mao; Zacharie Delpierre Jack Coudert; Zheng Jack Yan; Zhengxing Jack Chen; Zoe Jack Papakipos; Aaditya Jack Singh; Aaron Jack Grattafiori; Abha Jack Jain; Adam Jack Kelsey; Adam Jack Shajnfeld; Adithya Jack Gangidi; Adolfo Jack Victoria; Ahuva Jack Goldstand; Ajay Jack Menon; Ajay Jack Sharma; Alex Jack Boesenberg; Alex Jack Vaughan; Alexei Jack Baevski; Allie Jack Feinstein; Amanda Jack Kallet; Amit Jack Sangani; Anam Jack Yunus; Andrei Jack Lupu; Andres Jack Alvarado; Andrew Jack Caples; Andrew Jack Gu; Andrew Jack Ho; Andrew Jack Poulton; Andrew Jack Ryan; Ankit Jack Ramchandani; Annie Jack Franco; Aparajita Jack Saraf; Arkabandhu Jack Chowdhury; Ashley Jack Gabriel; Ashwin Jack Bharambe; Assaf Jack Eisenman; Azadeh Jack Yazdan; Beau Jack James; Ben Jack Maurer; Benjamin Jack Leonhardi; Bernie Jack Huang; Beth Jack Loyd; Paola Beto Jack De; Bhargavi Jack Paranjape; Bing Jack Liu; Bo Jack Wu; Boyu Jack Ni; Braden Jack Hancock; Bram Jack Wasti; Brandon Jack Spence; Brani Jack Stojkovic; Brian Jack Gamido; Britt Jack Montalvo; Carl Jack Parker; Carly Jack Burton; Catalina Jack Mejia; Changhan Jack Wang; Changkyu Jack Kim; Chao Jack Zhou; Chester Jack Hu; Ching-Hsiang Jack Chu; Chris Jack Cai; Chris Jack Tindal; Christoph Jack Feichtenhofer; Damon Jack Civin; Dana Jack Beaty; Daniel Jack Kreymer; Daniel Jack Li; Danny Jack Wyatt; David Jack Adkins; David Jack Xu; Davide Jack Testuggine; Delia Jack David; Devi Jack Parikh; Diana Jack Liskovich; Didem Jack Foss; Dingkang Jack Wang; Duc Jack Le; Dustin Jack Holland; Edward Jack Dowling; Eissa Jack Jamil; Elaine Jack Montgomery; Eleonora Jack Presani; Emily Jack Hahn; Emily Jack Wood; Erik Jack Brinkman; Esteban Jack Arcaute; Evan Jack Dunbar; Evan Jack Smothers; Fei Jack Sun; Felix Jack Kreuk; Feng Jack Tian; Firat Jack Ozgenel; Francesco Jack Caggioni; Francisco Jack Guzmán; Frank Jack Kanayet; Frank Jack Seide; Gabriela Medina Jack Florez; Gabriella Jack Schwarz; Gada Jack Badeer; Georgia Jack Swee; Gil Jack Halpern; Govind Jack Thattai; Grant Jack Herman; Grigory Jack Sizov; Jack Guangyi; Sid Zhang; Guna Sid Lakshminarayanan; Hamid Sid Shojanazeri; Han Sid Zou; Hannah Sid Wang; Hanwen Sid Zha; Haroun Sid Habeeb; Harrison Sid Rudolph; Helen Sid Suk; Henry Sid Aspegren; Hunter Sid Goldman; Igor Sid Molybog; Igor Sid Tufanov; Irina-Elena Sid Veliche; Itai Sid Gat; Jake Sid Weissman; James Sid Geboski; James Sid Kohli; Japhet Sid Asher; Jean-Baptiste Sid Gaya; Jeff Sid Marcus; Jeff Sid Tang; Jennifer Sid Chan; Jenny Sid Zhen; Jeremy Sid Reizenstein; Jeremy Sid Teboul; Jessica Sid Zhong; Jian Sid Jin; Jingyi Sid Yang; Joe Sid Cummings; Jon Sid Carvill; Jon Sid Shepard; Jonathan Sid McPhie; Jonathan Sid Torres; Josh Sid Ginsburg; Junjie Sid Wang; Kai Sid Wu; Kam Hou Sid U; Karan Sid Saxena; Karthik Sid Prasad; Kartikay Sid Khandelwal; Katayoun Sid Zand; Kathy Sid Matosich; Kaushik Sid Veeraraghavan; Kelly Sid Michelena; Keqian Sid Li; Kun Sid Huang; Kunal Sid Chawla; Kushal Sid Lakhotia; Kyle Sid Huang; Lailin Sid Chen; Lakshya Sid Garg; Lavender Sid A; Leandro Sid Silva; Lee Sid Bell; Lei Sid Zhang; Liangpeng Sid Guo; Licheng Sid Yu; Liron Sid Moshkovich; Luca Sid Wehrstedt; Madian Sid Khabsa; Manav Sid Avalani; Manish Sid Bhatt; Maria Sid Tsimpoukelli; Martynas Sid Mankus; Matan Sid Hasson; Matthew Sid Lennie; Matthias Sid Reso; Maxim Sid Groshev; Maxim Sid Naumov; Maya Sid Lathi; Meghan Sid Keneally; Michael L. Sid Seltzer; Michal Sid Valko; Michelle Sid Restrepo; Mihir Sid Patel; Mik Sid Vyatskov; Mikayel Sid Samvelyan; Mike Sid Clark; Mike Sid Macey; Mike Sid Wang; Miquel Jubert Sid Hermoso; Mo Sid Metanat; Mohammad Sid Rastegari; Munish Sid Bansal; Nandhini Sid Santhanam; Natascha Sid Parks; Natasha Sid White; Navyata Sid Bawa; Nayan Sid Singhal; Nick Sid Egebo; Nicolas Sid Usunier; Nikolay Pavlovich Sid Laptev; Ning Sid Dong; Ning Sid Zhang; Norman Sid Cheng; Oleg Sid Chernoguz; Olivia Sid Hart; Omkar Sid Salpekar; Ozlem Sid Kalinli; Parkin Sid Kent; Parth Sid Parekh; Paul Sid Saab; Pavan Sid Balaji; Pedro Sid Rittner; Philip Sid Bontrager; Pierre Sid Roux; Piotr Sid Dollar; Polina Sid Zvyagina; Prashant Sid Ratanchandani; Pritish Sid Yuvraj; Qian Sid Liang; Rachad Sid Alao; Rachel Sid Rodriguez; Rafi Sid Ayub; Raghotham Sid Murthy; Raghu Sid Nayani; Rahul Sid Mitra; Raymond Sid Li; Rebekkah Sid Hogan; Robin Sid Battey; Rocky Sid Wang; Rohan Sid Maheswari; Russ Sid Howes; Ruty Sid Rinott; Sai Jayesh Sid Bondu; Samyak Sid Datta; Sara Sid Chugh; Sara Sid Hunt; Sargun Sid Dhillon; Sasha Sid Sidorov; Satadru Sid Pan; Saurabh Sid Verma; Seiji Sid Yamamoto; Sharadh Sid Ramaswamy; Shaun Sid Lindsay; Shaun Sid Lindsay; Sheng Sid Feng; Shenghao Sid Lin; Shengxin Cindy Sid Zha; Shiva Sid Shankar; Shuqiang Sid Zhang; Shuqiang Sid Zhang; Sinong Sid Wang; Sneha Sid Agarwal; Soji Sid Sajuyigbe; Soumith Sid Chintala; Stephanie Sid Max; Stephen Sid Chen; Steve Sid Kehoe; Steve Sid Satterfield; Sudarshan Sid Govindaprasad; Sumit Sid Gupta; Sungmin Sid Cho; Sunny Sid Virk; Suraj Sid Subramanian; Sy Sid Choudhury; Sydney Sid Goldman; Tal Sid Remez; Tamar Sid Glaser; Tamara Sid Best; Thilo Sid Kohler; Thomas Sid Robinson; Tianhe Sid Li; Tianjun Sid Zhang; Tim Sid Matthews; Timothy Sid Chou; Tzook Sid Shaked; Varun Sid Vontimitta; Victoria Sid Ajayi; Victoria Sid Montanez; Vijai Sid Mohan; Vinay Satish Sid Kumar; Vishal Sid Mangla; Vlad Sid Ionescu; Vlad Sid Poenaru; Vlad Tiberiu Sid Mihailescu; Vladimir Sid Ivanov; Wei Sid Li; Wenchen Sid Wang; Wenwen Sid Jiang; Wes Sid Bouaziz; Will Sid Constable; Xiaocheng Sid Tang; Xiaofang Sid Wang; Xiaojian Sid Wu; Xiaolan Sid Wang; Xide Sid Xia; Xilun Sid Wu; Xinbo Sid Gao; Yanjun Sid Chen; Ye Sid Hu; Ye Sid Jia; Ye Sid Qi; Yenda Sid Li; Yilin Sid Zhang; Ying Sid Zhang; Yossi Sid Adi; Youngjin Sid Nam; Sid Yu; Wang; Yuchen Hao; Yundi Qian; Yuzi He; Zach Rait; Zachary DeVito; Zef Rosnbrick; Zhaoduo Wen; Zhenyu Yang; Zhiwei Zhao
Certifying Robustness of Learning-Based Keypoint Detection and Pose Estimation Methods. (22%)Xusheng Luo; Tianhao Wei; Simin Liu; Ziwei Wang; Luis Mattei-Mendez; Taylor Loper; Joshua Neighbor; Casidhe Hutchison; Changliu Liu
Vera Verto: Multimodal Hijacking Attack. (9%)Minxing Zhang; Ahmed Salem; Michael Backes; Yang Zhang
2024-07-30
Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks. (99%)Hunmin Yang; Jongoh Jeong; Kuk-Jin Yoon
AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning. (99%)Maisha Binte Rashid; Pablo Rivas
FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks. (99%)Hunmin Yang; Jongoh Jeong; Kuk-Jin Yoon
Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks. (99%)Yunfeng Diao; Naixin Zhai; Changtao Miao; Xun Yang; Meng Wang
Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models. (62%)Jiang Hao; Xiao Jin; Hu Xiaoguang; Chen Tianyou
DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers. (47%)C. A. Martínez-Mejía; J. Solano; J. Breier; D. Bucko; X. Hou
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification. (16%)Boyang Zhang; Yicong Tan; Yun Shen; Ahmed Salem; Michael Backes; Savvas Zannettou; Yang Zhang
Bayesian Low-Rank LeArning (Bella): A Practical Approach to Bayesian Neural Networks. (1%)Bao Gia Doan; Afshar Shamsi; Xiao-Yu Guo; Arash Mohammadi; Hamid Alinejad-Rokny; Dino Sejdinovic; Damith C. Ranasinghe; Ehsan Abbasnejad
2024-07-29
Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter. (99%)Chao Liu; Xin Liu; Zitong Yu; Yonghong Hou; Huanjing Yue; Jingyu Yang
Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent. (99%)Hetvi Waghela; Jaydip Sen; Sneha Rakshit
Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability. (92%)Jorge García-Carrasco; Alejandro Maté; Juan Trujillo
From ML to LLM: Evaluating the Robustness of Phishing Webpage Detection Models against Adversarial Attacks. (84%)Aditya Kulkarni; Vivek Balachandran; Dinil Mon Divakaran; Tamal Das
DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models. (68%)Jing Yang; Runping Xi; Yingxin Lai; Xun Lin; Zitong Yu
RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing Coding. (50%)Keming Wu; Man Yao; Yuhong Chou; Xuerui Qiu; Rui Yang; Bo Xu; Guoqi Li
Can Editing LLMs Inject Harm? (9%)Canyu Chen; Baixiang Huang; Zekun Li; Zhaorun Chen; Shiyang Lai; Xiongxiao Xu; Jia-Chen Gu; Jindong Gu; Huaxiu Yao; Chaowei Xiao; Xifeng Yan; William Yang Wang; Philip Torr; Dawn Song; Kai Shu
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning. (3%)Baoyuan Wu; Hongrui Chen; Mingda Zhang; Zihao Zhu; Shaokui Wei; Danni Yuan; Mingli Zhu; Ruotong Wang; Li Liu; Chao Shen
ImagiNet: A Multi-Content Dataset for Generalizable Synthetic Image Detection via Contrastive Learning. (1%)Delyan Boychev; Radostin Cholakov
2024-07-28
Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection. (80%)Rosa Vincenzo De; Fabrizio Guillaro; Giovanni Poggi; Davide Cozzolino; Luisa Verdoliva
2024-07-27
EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection. (99%)Shigang Liu; Di Cao; Junae Kim; Tamas Abraham; Paul Montague; Seyit Camtepe; Jun Zhang; Yang Xiang
Towards Clean-Label Backdoor Attacks in the Physical World. (98%)Thinh Dao; Cuong Chi Le; Khoa D Doan; Kok-Seng Wong
2024-07-26
Debiased Graph Poisoning Attack via Contrastive Surrogate Objective. (93%)Kanghoon Yoon; Yeonjun In; Namkyeong Lee; Kibum Kim; Chanyoung Park
Robust VAEs via Generating Process of Noise Augmented Data. (87%)Hiroo Irobe; Wataru Aoki; Kimihiro Yamazaki; Yuhui Zhang; Takumi Nakagawa; Hiroki Waida; Yuichiro Wada; Takafumi Kanamori
Adversarial Robustification via Text-to-Image Diffusion Models. (64%)Daewon Choi; Jongheon Jeong; Huiwon Jang; Jinwoo Shin
A Survey of Malware Detection Using Deep Learning. (5%)Ahmed Bensaoud; Jugal Kalita; Mahmoud Bensaoud
Unveiling Privacy Vulnerabilities: Investigating the Role of Structure in Graph Data. (1%)Hanyang Yuan; Jiarong Xu; Cong Wang; Ziqi Yang; Chunping Wang; Keting Yin; Yang Yang
UniForensics: Face Forgery Detection via General Facial Representation. (1%)Ziyuan Fang; Hanqing Zhao; Tianyi Wei; Wenbo Zhou; Ming Wan; Zhanyi Wang; Weiming Zhang; Nenghai Yu
2024-07-25
Sparse vs Contiguous Adversarial Pixel Perturbations in Multimodal Models: An Empirical Analysis. (99%)Cristian-Alexandru Botocan; Raphael Meier; Ljiljana Dolamic
Effects of Scale on Language Model Robustness. (96%)Nikolaus Howe; Ian McKenzie; Oskar Hollinsworth; Michał Zajac; Tom Tseng; Aaron Tucker; Pierre-Luc Bacon; Adam Gleave
A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models. (95%)Haonan Zheng; Xinyang Deng; Wen Jiang; Wenrui Li
RIDA: A Robust Attack Framework on Incomplete Graphs. (31%)Jianke Yu; Hanchen Wang; Chen Chen; Xiaoyang Wang; Wenjie Zhang; Ying Zhang
Adversarially Robust Decision Transformer. (22%)Xiaohang Tang; Afonso Marques; Parameswaran Kamalaruban; Ilija Bogunovic
Peak-Controlled Logits Poisoning Attack in Federated Distillation. (4%)Yuhan Tang; Aoxu Zhang; Zhiyuan Wu; Bo Gao; Tian Wen; Yuwei Wang; Sheng Sun
Network Inversion of Convolutional Neural Nets. (3%)Pirzada Suhail; Amit Sethi
Regret-Optimal Defense Against Stealthy Adversaries: A System Level Approach. (1%)Hiroyasu Tsukamoto; Joudi Hajar; Soon-Jo Chung; Fred Y. Hadaegh
2024-07-24
Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patches. (92%)Chenxing Zhao; Yang Li; Shihao Wu; Wenyi Tan; Shuangju Zhou; Quan Pan
FLRT: Fluent Student-Teacher Redteaming. (13%)T. Ben Confirm Labs Thompson; Michael Confirm Labs Sklar
2024-07-23
S-E Pipeline: A Vision Transformer (ViT) based Resilient Classification Pipeline for Medical Imaging Against Adversarial Attacks. (87%)Neha A S; Vivek Chaturvedi; Muhammad Shafique
Algebraic Adversarial Attacks on Integrated Gradients. (86%)Lachlan Simpson; Federico Costanza; Kyle Millar; Adriel Cheng; Cheng-Chew Lim; Hong Gunn Chew
Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning. (41%)Xinwei Liu; Xiaojun Jia; Yuan Xun; Siyuan Liang; Xiaochun Cao
When AI Defeats Password Deception! A Deep Learning Framework to Distinguish Passwords and Honeywords. (13%)Jimmy Dani; Brandon McCulloh; Nitesh Saxena
Figure it Out: Analyzing-based Jailbreak Attack on Large Language Models. (8%)Shi Lin; Rongchang Li; Xun Wang; Changting Lin; Wenpeng Xing; Meng Han
RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent. (5%)Huiyu Xu; Wenhui Zhang; Zhibo Wang; Feng Xiao; Rui Zheng; Yunhe Feng; Zhongjie Ba; Kui Ren
2024-07-22
Enhancing Transferability of Targeted Adversarial Examples: A Self-Universal Perspective. (99%)Bowen Peng; Li Liu; Tianpeng Liu; Zhen Liu; Yongxiang Liu
Towards Robust Vision Transformer via Masked Adaptive Ensemble. (99%)Fudong Lin; Jiadong Lou; Xu Yuan; Nian-Feng Tzeng
Towards Efficient Transferable Preemptive Adversarial Defense. (99%)Hanrui Wang; Ching-Chun Chang; Chun-Shien Lu; Isao Echizen
On Feasibility of Intent Obfuscating Attacks. (98%)Zhaobin Li; Patrick Shafto
Poisoning with A Pill: Circumventing Detection in Federated Learning. (92%)Hanxi Guo; Hao Wang; Tao Song; Tianhang Zheng; Yang Hua; Haibing Guan; Xiangyu Zhang
Revisiting the Robust Alignment of Circuit Breakers. (70%)Leo Schwinn; Simon Geisler
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs. (56%)Abhay Sheshadri; Aidan Ewart; Phillip Guo; Aengus Lynch; Cindy Wu; Vivek Hebbar; Henry Sleight; Asa Cooper Stickland; Ethan Perez; Dylan Hadfield-Menell; Stephen Casper
Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models. (11%)Xiao Liu; Liangzhi Li; Tong Xiang; Fuying Ye; Lu Wei; Wangyue Li; Noa Garcia
Virtual Reality and Augmented Reality Security: A Reconnaissance and Vulnerability Assessment Approach. (1%)Sarina Dastgerdy
2024-07-21
Taxonomy Driven Fast Adversarial Training. (99%)Kun Tong; Chengze Jiang; Jie Gui; Yuan Cao
When Do Universal Image Jailbreaks Transfer Between Vision-Language Models? (74%)Rylan Schaeffer; Dan Valentine; Luke Bailey; James Chua; Cristóbal Eyzaguirre; Zane Durante; Joe Benton; Brando Miranda; Henry Sleight; John Hughes; Rajashree Agrawal; Mrinank Sharma; Scott Emmons; Sanmi Koyejo; Ethan Perez
A Learning-Based Attack Framework to Break SOTA Poisoning Defenses in Federated Learning. (73%)Yuxin College of Computer Science and Technology, Jilin University Illinois Institute of Technology Yang; Qiang College of Computer Science and Technology, Jilin University Li; Chenfei College of Computer Science and Technology, Jilin University Nie; Yuan University of Connecticut Hong; Meng Nanchang University Pang; Binghui Illinois Institute of Technology Wang
SeqMIA: Sequential-Metric Based Membership Inference Attack. (22%)Hao Li; Zheng Li; Siyuan Wu; Chengrui Hu; Yutong Ye; Min Zhang; Dengguo Feng; Yang Zhang
Explainable AI-based Intrusion Detection System for Industry 5.0: An Overview of the Literature, associated Challenges, the existing Solutions, and Potential Research Directions. (5%)Naseem Khan; Kashif Ahmad; Aref Al Tamimi; Mohammed M. Alani; Amine Bermak; Issa Khalil
Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective. (2%)Mariya Hendriksen; Shuo Zhang; Ridho Reinanda; Mohamed Yahya; Edgar Meij; Rijke Maarten de
2024-07-20
Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models. (68%)Md Zarif Hossain; Ahmed Imteaj
2024-07-19
Data Poisoning: An Overlooked Threat to Power Grid Resilience. (68%)Nora Agah; Javad Mohammadi; Alex Aved; David Ferris; Erika Ardiles Cruz; Philip Morrone
Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context. (4%)Nilanjana Das; Edward Raff; Manas Gaur
Adversarial Databases Improve Success in Retrieval-based Large Language Models. (1%)Sean Wu; Michael Koo; Li Yo Kao; Andy Black; Lesley Blum; Fabien Scalzo; Ira Kurtz
On the Robustness of Fully-Spiking Neural Networks in Open-World Scenarios using Forward-Only Learning Algorithms. (1%)Erik B. Terres-Escudero; Ser Javier Del; Aitor Martínez-Seras; Pablo Garcia-Bringas
2024-07-18
Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shift. (99%)Qingyuan Zeng; Yunpeng Gong; Min Jiang
Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking. (98%)Yunpeng Gong; Chuangliang Zhang; Yongjie Hou; Lifei Chen; Min Jiang
Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models. (75%)Zhuo Chen; Jiawei Liu; Haotan Liu; Qikai Cheng; Fan Zhang; Wei Lu; Xiaozhong Liu
Prover-Verifier Games improve legibility of LLM outputs. (61%)Jan Hendrik Kirchner; Yining Chen; Harri Edwards; Jan Leike; Nat McAleese; Yuri Burda
Compressed models are NOT miniature versions of large models. (47%)Rohit Raj Rai; Rishant Pal; Amit Awekar
Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls. (16%)Aras Selvi; Eleonora Kreacic; Mohsen Ghassemi; Vamsi Potluru; Tucker Balch; Manuela Veloso
A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks. (10%)Yixiang Qiu; Hao Fang; Hongyao Yu; Bin Chen; MeiKang Qiu; Shu-Tao Xia
2024-07-17
PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving. (98%)Jiyuan Fu; Zhaoyu Chen; Kaixun Jiang; Haijing Guo; Shuyong Gao; Wenqiang Zhang
Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective. (98%)Zhaoxin Wang; Handing Wang; Cong Tian; Yaochu Jin
Transferable Adversarial Facial Images for Privacy Protection. (96%)Minghui Li; Jiangxiong Wang; Hao Zhang; Ziqi Zhou; Shengshan Hu; Xiaobing Pei
Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models. (86%)Haipeng Wang; Zhengyuan Wei; Qilin Zhou; Wing-Kwong Chan
Krait: A Backdoor Attack Against Graph Prompt Tuning. (83%)Ying Song; Rita Singh; Balaji Palanisamy
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases. (61%)Zhaorun Chen; Zhen Xiang; Chaowei Xiao; Dawn Song; Bo Li
Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks. (12%)Antoni Kowalczuk; Jan Dubiński; Atiyeh Ashari Ghomi; Yi Sui; George Stein; Jiapeng Wu; Jesse C. Cresswell; Franziska Boenisch; Adam Dziedzic
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models. (12%)Yong-Hyun Park; Sangdoo Yun; Jin-Hwa Kim; Junho Kim; Geonhui Jang; Yonghyun Jeong; Junghyo Jo; Gayoung Lee
Contrastive Adversarial Training for Unsupervised Domain Adaptation. (2%)Jiahong Chen; Zhilin Zhang; Lucy Li; Behzad Shahrasbi; Arjun Mishra
Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data. (1%)Wufei Ma; Kai Li; Zhongshi Jiang; Moustafa Meshry; Qihao Liu; Huiyu Wang; Christian Häne; Alan Yuille
2024-07-16
Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection. (99%)Youheng Sun; Shengming Yuan; Xuanhan Wang; Lianli Gao; Jingkuan Song
Variational Randomized Smoothing for Sample-Wise Adversarial Robustness. (99%)Ryo Hase; Ye Wang; Toshiaki Koike-Akino; Jing Liu; Kieran Parsons
AEMIM: Adversarial Examples Meet Masked Image Modeling. (99%)Wenzhao Xiang; Chang Liu; Hang Su; Hongyang Yu
Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysis. (99%)Zhipeng He; Chun Ouyang; Laith Alzubaidi; Alistair Barros; Catarina Moreira
Enhancing TinyML Security: Study of Adversarial Attack Transferability. (96%)Parin Shah; Yuvaraj Govindarajulu; Pavan Kulkarni; Manojkumar Parmar
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening. (82%)Siyuan Cheng; Guangyu Shen; Kaiyuan Zhang; Guanhong Tao; Shengwei An; Hanxi Guo; Shiqing Ma; Xiangyu Zhang
Relaxing Graph Transformers for Adversarial Attacks. (81%)Philipp Foth; Lukas Gosch; Simon Geisler; Leo Schwinn; Stephan Günnemann
Turning Generative Models Degenerate: The Power of Data Poisoning Attacks. (76%)Shuli Jiang; Swanand Ravindra Kadhe; Yi Zhou; Farhan Ahmed; Ling Cai; Nathalie Baracaldo
Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness. (33%)Kai Guo; Zewen Liu; Zhikai Chen; Hongzhi Wen; Wei Jin; Jiliang Tang; Yi Chang
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge. (33%)Hao Ding; Tuxun Lu; Yuqian Zhang; Ruixing Liang; Hongchao Shu; Lalithkumar Seenivasan; Yonghao Long; Qi Dou; Cong Gao; Mathias Unberath
Does Refusal Training in LLMs Generalize to the Past Tense? (15%)Maksym Andriushchenko; Nicolas Flammarion
Cover-separable Fixed Neural Network Steganography via Deep Generative Models. (8%)Guobiao Li; Sheng Li; Zhenxing Qian; Xinpeng Zhang
Model Inversion Attacks Through Target-Specific Conditional Diffusion Models. (4%)Ouxiang Li; Yanbin Hao; Zhicai Wang; Bin Zhu; Shuo Wang; Zaixi Zhang; Fuli Feng
IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields. (1%)Wenxiang Ocean University of China Jiang; Hanwei Saarland University Institute of Intelligent Software, Guangzhou Zhang; Shuo Ocean University of China Zhao; Zhongwen Ocean University of China Guo; Hao Xidian University, China Wang
2024-07-15
Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks. (99%)Quang H. Nguyen; Nguyen Ngoc-Hieu; The-Anh Ta; Thanh Nguyen-Tang; Kok-Seng Wong; Hoang Thanh-Tung; Khoa D. Doan
Backdoor Attacks against Image-to-Image Networks. (88%)Wenbo Jiang; Hongwei Li; Jiaming He; Rui Zhang; Guowen Xu; Tianwei Zhang; Rongxing Lu
Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques. (88%)Rishika Bhagwatkar; Shravan Nayak; Reza Bayat; Alexis Roger; Daniel Z Kaplan; Pouya Bashivan; Irina Rish
PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition. (80%)Xiao Li; Yining Liu; Na Dong; Sitian Qin; Xiaolin Hu
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks. (67%)Lukas Gosch; Mahalakshmi Sabanayagam; Debarghya Ghoshdastidar; Stephan Günnemann
Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models. (41%)Qingcheng Zeng; Mingyu Jin; Qinkai Yu; Zhenting Wang; Wenyue Hua; Zihao Zhou; Guangyan Sun; Yanda Meng; Shiqing Ma; Qifan Wang; Felix Juefei-Xu; Kaize Ding; Fan Yang; Ruixiang Tang; Yongfeng Zhang
Feature Inference Attack on Shapley Values. (12%)Xinjian Luo; Yangfan Jiang; Xiaokui Xiao
2024-07-14
Transferable 3D Adversarial Shape Completion using Diffusion Models. (99%)Xuelong Dai; Bin Xiao
Towards Robust Recommendation via Decision Boundary-aware Graph Contrastive Learning. (92%)Jiakai Tang; Sunhao Dai; Zexu Sun; Xu Chen; Jun Xu; Wenhui Yu; Lantao Hu; Peng Jiang; Han Li
Defending Against Repetitive-based Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off. (76%)Cheng-Yi Lee; Ching-Chia Kao; Cheng-Han Yeh; Chun-Shien Lu; Chia-Mu Yu; Chu-Song Chen
CLIP-Guided Networks for Transferable Targeted Attacks. (76%)Hao Fang; Jiawei Kong; Bin Chen; Tao Dai; Hao Wu; Shu-Tao Xia
SENTINEL: Securing Indoor Localization against Adversarial Attacks with Capsule Neural Networks. (10%)Danish Gufran; Pooja Anandathirtha; Sudeep Pasricha
2024-07-13
Augmented Neural Fine-Tuning for Efficient Backdoor Purification. (68%)Nazmul Karim; Abdullah Al Arafat; Umar Khalid; Zhishan Guo; Nazanin Rahnavard
Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning. (67%)Shihua Sun; Shridatt Sugrim; Angelos Stavrou; Haining Wang
Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs. (1%)Jiahuan Yan; Jintai Chen; Qianxing Wang; Danny Z. Chen; Jian Wu
2024-07-12
SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images. (99%)Mingyuan Fan; Yang Liu; Cen Chen; Ximeng Liu
Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off. (97%)Levente Halmosi; Bálint Mohos; Márk Jelasity
TAPI: Towards Target-Specific and Adversarial Prompt Injection against Code LLMs. (93%)Yuchen Yang; Hongwei Yao; Bingrun Yang; Yiling He; Yiming Li; Tianwei Zhang; Zhan Qin; Kui Ren
Deep Adversarial Defense Against Multilevel-Lp Attacks. (87%)Ren Wang; Yuxuan Li; Alfred Hero
Robust Yet Efficient Conformal Prediction Sets. (61%)Soroush H. Zargarbashi; Mohammad Sadegh Akhondzadeh; Aleksandar Bojchevski
Refusing Safe Prompts for Multi-modal Large Language Models. (16%)Zedian Shao; Hongbin Liu; Yuepeng Hu; Neil Zhenqiang Gong
Security Matrix for Multimodal Agents on Mobile Devices: A Systematic and Proof of Concept Study. (15%)Yulong Yang; Xinshan Yang; Shuaidong Li; Chenhao Lin; Zhengyu Zhao; Chao Shen; Tianwei Zhang
MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants. (13%)John Heibel; Daniel Lowd
BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning. (5%)Ning Wang; Shanghao Shi; Yang Xiao; Yimin Chen; Y. Thomas Hou; Wenjing Lou
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training. (1%)Youliang Yuan; Wenxiang Jiao; Wenxuan Wang; Jen-tse Huang; Jiahao Xu; Tian Liang; Pinjia He; Zhaopeng Tu
2024-07-11
Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systems. (99%)Yuxin Cao; Yumeng Zhu; Derui Wang; Sheng Wen; Minhui Xue; Jin Lu; Hao Ge
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space. (99%)Yunfeng Diao; Baiqi Wu; Ruixuan Zhang; Xun Yang; Meng Wang; He Wang
HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks. (98%)Raffaele Mura; Giuseppe Floris; Luca Scionis; Giorgio Piras; Maura Pintor; Ambra Demontis; Giorgio Giacinto; Battista Biggio; Fabio Roli
Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses. (98%)Yuxin College of Computer Science and Technology, Jilin University Illinois Institute of Technology Yang; Qiang College of Computer Science and Technology, Jilin University Li; Jinyuan The Pennsylvania State University Jia; Yuan University of Connecticut Hong; Binghui Illinois Institute of Technology Wang
DeCE: Deceptive Cross-Entropy Loss Designed for Defending Backdoor Attacks. (87%)Guang Yang; Yu Zhou; Xiang Chen; Xiangyu Zhang; Terry Yue Zhuo; David Lo; Taolue Chen
How to beat a Bayesian adversary. (81%)Zihan Ding; Kexin Jin; Jonas Latz; Chenguang Liu
Soft Prompts Go Hard: Steering Visual Language Models with Hidden Meta-Instructions. (74%)Tingwei Zhang; Collin Zhang; John X. Morris; Eugene Bagdasarian; Vitaly Shmatikov
DART: A Solution for Decentralized Federated Learning Model Robustness Analysis. (47%)Chao Feng; Alberto Huertas Celdrán; der Assen Jan von; Enrique Tomás Martínez Beltrán; Gérôme Bovet; Burkhard Stiller
Quantitative Evaluation of the Saliency Map for Alzheimer's Disease Classifier with Anatomical Segmentation. (8%)Yihan Zhang; Xuanshuo Zhang; Wei Wu; Haohan Wang
Enhancing Privacy of Spatiotemporal Federated Learning against Gradient Inversion Attacks. (8%)Lele Zheng; Yang Cao; Renhe Jiang; Kenjiro Taura; Yulong Shen; Sheng Li; Masatoshi Yoshikawa
Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation. (1%)Riccardo Cantini; Giada Cosenza; Alessio Orsino; Domenico Talia
Deep Learning for Network Anomaly Detection under Data Contamination: Evaluating Robustness and Mitigating Performance Degradation. (1%)D'Jeff K. Nkashama; Jordan Masakuna Félicien; Arian Soltani; Jean-Charles Verdier; Pierre-Martin Tardif; Marc Frappier; Froduald Kabanza
2024-07-10
Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey. (99%)Chenyu Zhang; Mingwang Hu; Wenhui Li; Lanjun Wang
A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends. (38%)Daizong Liu; Mingyu Yang; Xiaoye Qu; Pan Zhou; Wei Hu; Yu Cheng
Model-agnostic clean-label backdoor mitigation in cybersecurity environments. (31%)Giorgio Severi; Simona Boboila; John Holodnak; Kendra Kratkiewicz; Rauf Izmailov; Lucia Michael J. De; Alina Oprea
Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities. (11%)Tianjie Ju; Yiting Wang; Xinbei Ma; Pengzhou Cheng; Haodong Zhao; Yulong Wang; Lifeng Liu; Jian Xie; Zhuosheng Zhang; Gongshen Liu
Invisible Optical Adversarial Stripes on Traffic Sign against Autonomous Vehicles. (8%)Dongfang Guo; Yuting Wu; Yimin Dai; Pengfei Zhou; Xin Lou; Rui Tan
A Comprehensive Survey on the Security of Smart Grid: Challenges, Mitigations, and Future Research Opportunities. (2%)Arastoo Zibaeirad; Farnoosh Koleini; Shengping Bi; Tao Hou; Tao Wang
Was it Slander? Towards Exact Inversion of Generative Language Models. (2%)Adrians Skapars; Edoardo Manino; Youcheng Sun; Lucas C. Cordeiro
CHILLI: A data context-aware perturbation method for XAI. (1%)Saif Anwar; Nathan Griffiths; Abhir Bhalerao; Thomas Popham
2024-07-09
A Hybrid Training-time and Run-time Defense Against Adversarial Attacks in Modulation Classification. (99%)Lu Zhang; Sangarapillai Lambotharan; Gan Zheng; Guisheng Liao; Ambra Demontis; Fabio Roli
Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization. (99%)Donghua Wang; Wen Yao; Tingsong Jiang; Chao Li; Xiaoqian Chen
DLOVE: A new Security Evaluation Tool for Deep Learning Based Watermarking Techniques. (98%)Sudev Kumar Padhi; Sk. Subidh Ali
Countermeasures Against Adversarial Examples in Radio Signal Classification. (97%)Lu Zhang; Sangarapillai Lambotharan; Gan Zheng; Basil AsSadhan; Fabio Roli
Improving the Transferability of Adversarial Examples by Feature Augmentation. (93%)Donghua Wang; Wen Yao; Tingsong Jiang; Xiaohu Zheng; Junqi Wu; Xiaoqian Chen
Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning. (26%)Yuqi Jia; Minghong Fang; Hongbin Liu; Jinghuai Zhang; Neil Zhenqiang Gong
The Quantum Imitation Game: Reverse Engineering of Quantum Machine Learning Models. (15%)Archisman Ghosh; Swaroop Ghosh
Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective. (13%)Yu-An Liu; Ruqing Zhang; Jiafeng Guo; Rijke Maarten de; Yixing Fan; Xueqi Cheng
Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryption. (10%)Umesh Kashyap; Sudev Kumar Padhi; Sk. Subidh Ali
Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attacks. (8%)Sourabh Kapoor; Arnab Sharma; Michael Röder; Caglar Demir; Axel-Cyrille Ngonga Ngomo
Exploring the Causality of End-to-End Autonomous Driving. (1%)Jiankun Li; Hao Li; Jiangjiang Liu; Zhikang Zou; Xiaoqing Ye; Fan Wang; Jizhou Huang; Hua Wu; Haifeng Wang
Distribution System Reconfiguration to Mitigate Load Altering Attacks via Stackelberg Games. (1%)Sajjad Maleki; Subhash Lakshminarayana; Charalambos Konstantinou; E. Veronica Belmaga
2024-07-08
Shedding More Light on Robust Classifiers under the lens of Energy-based Models. (98%)Mujtaba Hussain Mirza; Maria Rosaria Briglia; Senad Beadini; Iacopo Masi
Non-Robust Features are Not Always Useful in One-Class Classification. (92%)Matthew Lau; Haoran Wang; Alec Helbling; Matthew Hul; ShengYun Peng; Martin Andreoni; Willian T. Lunardi; Wenke Lee
Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment. (1%)Qizhang Feng; Siva Rajesh Kasa; Hyokun Yun; Choon Hui Teo; Sravan Babu Bodapati
2024-07-07
Rethinking Targeted Adversarial Attacks For Neural Machine Translation. (99%)Junjie Wu; Lemao Liu; Wei Bi; Dit-Yan Yeung
Gradient Diffusion: A Perturbation-Resilient Gradient Leakage Attack. (64%)Xuan Liu; Siqi Cai; Qihua Zhou; Song Guo; Ruibin Li; Kaiwei Lin
An accurate detection is not all you need to combat label noise in web-noisy datasets. (1%)Paul Albert; Jack Valmadre; Eric Arazo; Tarun Krishna; Noel E. O'Connor; Kevin McGuinness
Detecting new obfuscated malware variants: A lightweight and interpretable machine learning approach. (1%)Oladipo A. Madamidola; Felix Ngobigha; Adnane Ez-zizi
Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense. (1%)Qi Zhou; Zipeng Ye; Yubo Tang; Wenjian Luo; Yuhui Shi; Yan Jia
2024-07-06
A Novel Bifurcation Method for Observation Perturbation Attacks on Reinforcement Learning Agents: Load Altering Attacks on a Cyber Physical Power System. (99%)Kiernan Broda-Milian; Ranwa Al-Mallah; Hanane Dagdougui
Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning. (13%)Binhao Ma; Tianhang Zheng; Hongsheng Hu; Di Wang; Shuo Wang; Zhongjie Ba; Zhan Qin; Kui Ren
GCON: Differentially Private Graph Convolutional Network via Objective Perturbation. (12%)Jianxin Wei; Yizheng Zhu; Xiaokui Xiao; Ergute Bao; Yin Yang; Kuntai Cai; Beng Chin Ooi
2024-07-05
Remembering Everything Makes You Vulnerable: A Limelight on Machine Unlearning for Personalized Healthcare Sector. (98%)Ahan Chatterjee; Sai Anirudh Aryasomayajula; Rajat Chaudhari; Subhajit Paul; Vishwa Mohan Singh
Jailbreak Attacks and Defenses Against Large Language Models: A Survey. (92%)Sibo Yi; Yule Liu; Zhen Sun; Tianshuo Cong; Xinlei He; Jiaxing Song; Ke Xu; Qi Li
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models. (91%)Vyas Raina; Mark Gales
Self-Supervised Representation Learning for Adversarial Attack Detection. (68%)Yi Li; Plamen Angelov; Neeraj Suri
On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks. (61%)Zesen Liu; Tianshuo Cong; Xinlei He; Qi Li
Late Breaking Results: Fortifying Neural Networks: Safeguarding Against Adversarial Attacks with Stochastic Computing. (54%)Faeze S. Banitaba; Sercan Aygun; M. Hassan Najafi
Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density. (38%)Peiyu Yang; Naveed Akhtar; Mubarak Shah; Ajmal Mian
Data Poisoning Attacks in Intelligent Transportation Systems: A Survey. (2%)Feilong Wang; Xin Wang; Xuegang Ban
Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape. (2%)Tuan Nguyen; Dung Thuy Nguyen; Khoa D Doan; Kok-Seng Wong
2024-07-04
TrackPGD: A White-box Attack using Binary Masks against Robust Transformer Trackers. (99%)Fatemeh Nourilenjan Nokabadi; Yann Batiste Pequignot; Jean-Francois Lalonde; Christian Gagné
Protecting Deep Learning Model Copyrights with Adversarial Example-Free Reuse Detection. (99%)Xiaokun Luan; Xiyue Zhang; Jingyi Wang; Meng Sun
Adversarial Robustness of VAEs across Intersectional Subgroups. (99%)Chethan Krishnamurthy Ramanaik; Arjun Roy; Eirini Ntoutsi
Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness. (92%)Kejia Zhang; Juanjuan Weng; Yuanzheng Cai; Zhiming Luo; Shaozi Li
Securing Multi-turn Conversational Language Models Against Distributed Backdoor Triggers. (68%)Terry Tong; Jiashu Xu; Qin Liu; Muhao Chen
Charging Ahead: A Hierarchical Adversarial Framework for Counteracting Advanced Cyber Threats in EV Charging Stations. (15%)Mohammed Al-Mehdhar; Abdullatif Albaseer; Mohamed Abdallah; Ala Al-Fuqaha
T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models. (13%)Zhongqi Wang; Jie Zhang; Shiguang Shan; Xilin Chen
Automated Progressive Red Teaming. (2%)Bojian Jiang; Yi Jing; Tianhao Shen; Tong Wu; Qing Yang; Deyi Xiong
Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs. (1%)Faisal Hamman; Pasan Dissanayake; Saumitra Mishra; Freddy Lecue; Sanghamitra Dutta
Certifiably Robust Image Watermark. (1%)Zhengyuan Jiang; Moyang Guo; Yuepeng Hu; Jinyuan Jia; Neil Zhenqiang Gong
2024-07-03
A Wolf in Sheep's Clothing: Practical Black-box Adversarial Attacks for Evading Learning-based Windows Malware Detection in the Wild. (99%)Xiang Ling; Zhiyu Wu; Bin Wang; Wei Deng; Jingzheng Wu; Shouling Ji; Tianyue Luo; Yanjun Wu
$L_p$-norm Distortion-Efficient Adversarial Attack. (99%)Chao Zhou; Yuan-Gen Wang; Zi-jia Wang; Xiangui Kang
SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing. (98%)Meiyu Zhong; Ravi Tandon
JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasets. (83%)Zhihua Jin; Shiyi Liu; Haotian Li; Xun Zhao; Huamin Qu
Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learning. (74%)Son Nguyen; Thinh Nguyen; Khoa Doan; Kok-Seng Wong
A Geometric Framework for Adversarial Vulnerability in Machine Learning. (70%)Brian Bell
Self-Evaluation as a Defense Against Adversarial Attacks on LLMs. (41%)Hannah Brown; Leon Lin; Kenji Kawaguchi; Michael Shieh
Backdoor Graph Condensation. (16%)Jiahao Wu; Ning Lu; Zeiyu Dai; Wenqi Fan; Shengcai Liu; Qing Li; Ke Tang
Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks. (10%)Zhexin Zhang; Junxiao Yang; Pei Ke; Shiyao Cui; Chujie Zheng; Hongning Wang; Minlie Huang
Federated Learning for Zero-Day Attack Detection in 5G and Beyond V2X Networks. (2%)Abdelaziz Amara korba; Abdelwahab Boualouache; Bouziane Brik; Rabah Rahal; Yacine Ghamri-Doudane; Sidi Mohammed Senouci
An Empirical Study on Capability of Large Language Models in Understanding Code Semantics. (1%)Thu-Trang Nguyen; Thanh Trong Vu; Hieu Dinh Vo; Son Nguyen
On Large Language Models in National Security Applications. (1%)William N. Caballero; Phillip R. Jenkins
Purification Of Contaminated Convolutional Neural Networks Via Robust Recovery: An Approach with Theoretical Guarantee in One-Hidden-Layer Case. (1%)Hanxiao Lu; Zeyu Huang; Ren Wang
2024-07-02
Secure Semantic Communication via Paired Adversarial Residual Networks. (99%)Boxiang He; Fanggang Wang; Tony Q. S. Quek
EvolBA: Evolutionary Boundary Attack under Hard-label Black Box condition. (99%)Ayane Tajima; Satoshi Ono
Adversarial Magnification to Deceive Deepfake Detection through Super Resolution. (98%)Davide Alessandro Coccomini; Roberto Caldelli; Giuseppe Amato; Fabrizio Falchi; Claudio Gennaro
Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses. (80%)David Glukhov; Ziwen Han; Ilia Shumailov; Vardan Papyan; Nicolas Papernot
Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models. (76%)Xu Han; Linghao Jin; Xuezhe Ma; Xiaofeng Liu
Parameter Matching Attack: Enhancing Practical Applicability of Availability Attacks. (50%)Yu Zhe; Jun Sakuma
Towards More Realistic Extraction Attacks: An Adversarial Perspective. (22%)Yash More; Prakhar Ganesh; Golnoosh Farnadi
On the Robustness of Graph Reduction Against GNN Backdoor. (13%)Yuxuan Zhu; Michael Mandulak; Kerui Wu; George Slota; Yuseok Jeon; Ka-Ho Chow; Lei Yu
MALT Powers Up Adversarial Attacks. (13%)Odelia Melamed; Gilad Yehudai; Adi Shamir
Face Reconstruction Transfer Attack as Out-of-Distribution Generalization. (2%)Yoon Gyo Jung; Jaewoo Park; Xingbo Dong; Hojin Park; Andrew Beng Jin Teoh; Octavia Camps
Robust ADAS: Enhancing Robustness of Machine Learning-based Advanced Driver Assistance Systems for Adverse Weather. (1%)Muhammad Zaeem Shahzad; Muhammad Abdullah Hanif; Muhammad Shafique
2024-07-01
Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid. (98%)Kalibinuer Tiliwalidi; Chengyin Hu; Weiwen Shi
DeepiSign-G: Generic Watermark to Stamp Hidden DNN Parameters for Self-contained Tracking. (82%)Alsharif Abuadbba; Nicholas Rhodes; Kristen Moore; Bushra Sabir; Shuo Wang; Yansong Gao
Looking From the Future: Multi-order Iterations Can Enhance Adversarial Attack Transferability. (81%)Zijian Ying; Qianmu Li; Tao Wang; Zhichao Lian; Shunmei Meng; Xuyun Zhang
QUEEN: Query Unlearning against Model Extraction. (75%)Huajie Chen; Tianqing Zhu; Lefeng Zhang; Bo Liu; Derui Wang; Wanlei Zhou; Minhui Xue
Formal Verification of Object Detection. (56%)Avraham Raviv; Yizhak Y. Elboher; Michelle Aluf-Medina; Yael Leibovich Weiss; Omer Cohen; Roy Assa; Guy Katz; Hillel Kugler
SoP: Unlock the Power of Social Facilitation for Automatic Jailbreak Attack. (13%)Yan Yang; Zeguan Xiao; Xin Lu; Hongru Wang; Hailiang Huang; Guanhua Chen; Yun Chen
Securing Distributed Network Digital Twin Systems Against Model Poisoning Attacks. (8%)Zifan Zhang; Minghong Fang; Mingzhe Chen; Gaolei Li; Xi Lin; Yuchen Liu
A Fingerprint for Large Language Models. (2%)Zhiguang Yang; Hanzhou Wu
Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability. (1%)Chenxi Li; Abhinav Kumar; Zhen Guo; Jie Hou; Reza Tourani
Unaligning Everything: Or Aligning Any Text to Any Image in Multimodal Models. (1%)Shaeke Salman; Md Montasir Bin Shams; Xiuwen Liu
2024-06-30
Learning Robust 3D Representation from CLIP via Dual Denoising. (67%)Shuqing Luo; Bowen Qu; Wei Gao
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness. (13%)Yiquan Li; Zhongzhu Chen; Kun Jin; Jiongxiao Wang; Bo Li; Chaowei Xiao
UWBAD: Towards Effective and Imperceptible Jamming Attacks Against UWB Ranging Systems with COTS Chips. (2%)Yuqiao Yang; Zhongjie Wu; Yongzhao Zhang; Ting Chen; Jun Li; Jie Yang; Wenhao Liu; Xiaosong Zhang; Ruicong Shi; Jingwei Li; Yu Jiang; Zhuo Su
2024-06-29
Query-Efficient Hard-Label Black-Box Attack against Vision Transformers. (99%)Chao Zhou; Xiaowen Shi; Yuan-Gen Wang
2024-06-28
Deceptive Diffusion: Generating Synthetic Adversarial Examples. (99%)Lucas Beerens; Catherine F. Higham; Desmond J. Higham
DiffuseDef: Improved Robustness to Adversarial Attacks. (95%)Zhenhao Li; Marek Rei; Lucia Specia
Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features. (92%)Feng Liu; Qing Xu; Qijian Zheng
Steering cooperation: Adversarial attacks on prisoner's dilemma in complex networks. (92%)Kazuhiro Takemoto
IDT: Dual-Task Adversarial Attacks for Privacy Protection. (88%)Pedro Faustini; Shakila Mahjabin Tonni; Annabelle McIver; Qiongkai Xu; Mark Dras
Backdoor Attack in Prompt-Based Continual Learning. (16%)Trang Nguyen; Anh Tran; Nhat Ho
Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection. (11%)Yuqi Zhou; Lin Lu; Hanchi Sun; Pan Zhou; Lichao Sun
GRACE: Graph-Regularized Attentive Convolutional Entanglement with Laplacian Smoothing for Robust DeepFake Video Detection. (1%)Chih-Chung Hsu; Shao-Ning Chen; Mei-Hsuan Wu; Yi-Fang Wang; Chia-Ming Lee; Yi-Shiuan Chou
2024-06-27
Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems. (99%)Zheng Fang; Tao Wang; Lingchen Zhao; Shenyi Zhang; Bowen Li; Yunjie Ge; Qi Li; Chao Shen; Qian Wang
Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness. (98%)Erh-Chung Chen; Pin-Yu Chen; I-Hsin Chung; Che-Rung Lee
Investigating and Defending Shortcut Learning in Personalized Diffusion Models. (87%)Yixin Liu; Ruoxi Chen; Lichao Sun
Data Poisoning Attacks to Locally Differentially Private Frequent Itemset Mining Protocols. (2%)Wei Tong; Haoyu Chen; Jiacheng Niu; Sheng Zhong
Context Matters: An Empirical Study of the Impact of Contextual Information in Temporal Question Answering Systems. (1%)Dan Schumacher; Fatemeh Haji; Tara Grey; Niharika Bandlamudi; Nupoor Karnik; Gagana Uday Kumar; Jason Cho-Yu Chiang; Paul Rad; Nishant Vishwamitra; Anthony Rios
2024-06-26
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers. (98%)Jonas Ngnawé; Sabyasachi Sahoo; Yann Pequignot; Frédéric Precioso; Christian Gagné
On Discrete Prompt Optimization for Diffusion Models. (62%)Ruochen Wang; Ting Liu; Cho-Jui Hsieh; Boqing Gong
Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents. (54%)Chung-En Sun; Sicun Gao; Tsui-Wei Weng
Poisoned LangChain: Jailbreak LLMs by LangChain. (26%)Ziqiu Wang; Jun Liu; Shengkai Zhang; Yang Yang
Revisiting Backdoor Attacks against Large Vision-Language Models. (15%)Siyuan Liang; Jiawei Liang; Tianyu Pang; Chao Du; Aishan Liu; Ee-Chien Chang; Xiaochun Cao
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models. (12%)Liwei Jiang; Kavel Rao; Seungju Han; Allyson Ettinger; Faeze Brahman; Sachin Kumar; Niloofar Mireshghallah; Ximing Lu; Maarten Sap; Yejin Choi; Nouha Dziri
Adversarial Search Engine Optimization for Large Language Models. (9%)Fredrik Nestaas; Edoardo Debenedetti; Florian Tramèr
2024-06-25
CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems. (99%)Zhen Chen; Yong Liao; Youpeng Zhao; Zipeng Dai; Jian Zhao
Diffusion-based Adversarial Purification for Intrusion Detection. (98%)Mohamed Amine Merzouk; Erwan Beurier; Reda Yaich; Nora Boulahia-Cuppens; Frédéric Cuppens
Semantic Deep Hiding for Robust Unlearnable Examples. (76%)Ruohan Meng; Chenyu Yi; Yi Yu; Siyuan Yang; Bingquan Shen; Alex C. Kot
Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness. (67%)Vaclav Voracek
Robustly Optimized Deep Feature Decoupling Network for Fatty Liver Diseases Detection. (13%)Peng Huang; Shu Hu; Bo Peng; Jiashu Zhang; Xi Wu; Xin Wang
2024-06-24
Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances. (98%)Emma Hart; Quentin Renau; Kevin Sim; Mohamad Alissa
UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification. (96%)Alvaro Lopez Pellicer; Kittipos Giatgong; Yi Li; Neeraj Suri; Plamen Angelov
ADVSCORE: A Metric for the Evaluation and Creation of Adversarial Benchmarks. (92%)Yoo Yeon Sung; Eve Fleisig; Ishani Mondal; Jordan Lee Boyd-Graber
Automated Adversarial Discovery for Safety Classifiers. (92%)Yash Kumar Lal; Preethi Lahoti; Aradhana Sinha; Yao Qin; Ananth Balashankar
Improving robustness to corruptions with multiplicative weight perturbations. (74%)Trung Trinh; Markus Heinonen; Luigi Acerbi; Samuel Kaski
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models. (38%)Yi Zeng; Weiyu Sun; Tran Ngoc Huynh; Dawn Song; Bo Li; Ruoxi Jia
From Perfect to Noisy World Simulation: Customizable Embodied Multi-modal Perturbations for SLAM Robustness Benchmarking. (5%)Xiaohao Xu; Tianyi Zhang; Sibo Wang; Xiang Li; Yongqi Chen; Ye Li; Bhiksha Raj; Matthew Johnson-Roberson; Xiaonan Huang
Machine Unlearning Fails to Remove Data Poisoning Attacks. (2%)Martin Pawelczyk; Jimmy Z. Di; Yiwei Lu; Gautam Kamath; Ayush Sekhari; Seth Neel
2024-06-23
Towards unlocking the mystery of adversarial fragility of neural networks. (64%)Jingchao Gao; Raghu Mudumbai; Xiaodong Wu; Jirong Yi; Catherine Xu; Hui Xie; Weiyu Xu
CBPF: Filtering Poisoned Data Based on Composite Backdoor Attack. (13%)Hanfeng Xia; Haibo Hong; Ruili Wang
Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection. (8%)Choonghyun Park; Hyuhng Joon Kim; Junyeob Kim; Youna Kim; Taeuk Kim; Hyunsoo Cho; Hwiyeol Jo; Sang-goo Lee; Kang Min Yoo
On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction. (2%)Tianyu Han; Sven Nebelung; Firas Khader; Jakob Nikolas Kather; Daniel Truhn
Understanding and Diagnosing Deep Reinforcement Learning. (1%)Ezgi Korkmaz
2024-06-22
The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI. (97%)Christopher Burger; Charles Walter; Thai Le
Federated Adversarial Learning for Robust Autonomous Landing Runway Detection. (2%)Yi Li; Plamen Angelov; Zhengxin Yu; Alvaro Lopez Pellicer; Neeraj Suri
Privacy Implications of Explainable AI in Data-Driven Systems. (1%)Fatima Ezzeddine
2024-06-21
ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification. (99%)Xianlong Wang; Shengshan Hu; Yechao Zhang; Ziqi Zhou; Leo Yu Zhang; Peng Xu; Wei Wan; Hai Jin
Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors. (99%)Peter Lorenz; Mario Fernandez; Jens Müller; Ullrich Köthe
DataFreeShield: Defending Adversarial Attacks without Training Data. (45%)Hyeyoon Lee; Kanghyun Choi; Dain Kwon; Sunjong Park; Mayoore Selvarasa Jaiswal; Noseong Park; Jonghyun Choi; Jinho Lee
Large Language Models for Link Stealing Attacks Against Graph Neural Networks. (38%)Faqian Guan; Tianqing Zhu; Hui Sun; Wanlei Zhou; Philip S. Yu
Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference. (2%)Anton Xue; Avishree Khare; Rajeev Alur; Surbhi Goel; Eric Wong
MOUNTAINEER: Topology-Driven Visual Analytics for Comparing Local Explanations. (1%)Parikshit Solunke; Vitoria Guardieiro; Joao Rulff; Peter Xenopoulos; Gromit Yeuk-Yin Chan; Brian Barr; Luis Gustavo Nonato; Claudio Silva
2024-06-20
Enhancing robustness of data-driven SHM models: adversarial training with circle loss. (99%)Xiangli Yang; Xijie Deng; Hanwei Zhang; Yang Zou; Jianxi Yang
Exploring Layerwise Adversarial Robustness Through the Lens of t-SNE. (87%)Inês Valentim; Nuno Antunes; Nuno Lourenço
Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning. (81%)Yujing Wang; Hainan Zhang; Sijia Wen; Wangjie Qiu; Binghui Guo
Jailbreaking as a Reward Misspecification Problem. (78%)Zhihui Xie; Jiahui Gao; Lei Li; Zhenguo Li; Qi Liu; Lingpeng Kong
Uniform Convergence of Adversarially Robust Classifiers. (68%)Rachel Morris; Ryan Murray
Prompt Injection Attacks in Defended Systems. (47%)Daniil Khomsky; Narek Maloyan; Bulat Nutfullin
MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization. (41%)Zhaozhe Hu; Jia-Li Yin; Bin Chen; Luojun Lin; Bo-Hao Chen; Ximeng Liu
Countering adversarial perturbations in graphs using error correcting codes. (22%)Saif Eddin Jabari
Steering Without Side Effects: Improving Post-Deployment Control of Language Models. (15%)Asa Cooper Stickland; Alexander Lyzhov; Jacob Pfau; Salsabila Mahdi; Samuel R. Bowman
Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective. (8%)Yuchen Wen; Keping Bi; Wei Chen; Jiafeng Guo; Xueqi Cheng
PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions. (5%)Sihan Ma; Jing Zhang; Qiong Cao; Dacheng Tao
Can you trust your explanations? A robustness test for feature attribution methods. (2%)Ilaria Vascotto; Alex Rodriguez; Alessandro Bonaita; Luca Bortolussi
SeCTIS: A Framework to Secure CTI Sharing. (1%)Dincy R. Arikkat; Mert Cihangiroglu; Mauro Conti; Rafidha Rehiman K. A.; Serena Nicolazzo; Antonino Nocera; Vinod P
2024-06-19
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning. (99%)Tao Wu; Xinwen Cao; Chao Wang; Shaojie Qiao; Xingping Xian; Lin Yuan; Canyixing Cui; Yanbing Liu
AGSOA:Graph Neural Network Targeted Attack Based on Average Gradient and Structure Optimization. (99%)Yang Chen; Bin Zhou
Explainable AI Security: Exploring Robustness of Graph Neural Networks to Adversarial Attacks. (99%)Tao Wu; Canyixing Cui; Xingping Xian; Shaojie Qiao; Chao Wang; Lin Yuan; Shui Yu
AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents. (83%)Edoardo Debenedetti; Jie Zhang; Mislav Balunović; Luca Beurer-Kellner; Marc Fischer; Florian Tramèr
Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokens. (62%)Xikang Yang; Xuehai Tang; Fuqing Zhu; Jizhong Han; Songlin Hu
Textual Unlearning Gives a False Sense of Unlearning. (16%)Jiacheng Du; Zhibo Wang; Kui Ren
Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation. (9%)Björn Nieth; Thomas Altstidl; Leo Schwinn; Björn Eskofier
DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection. (3%)Zhuoxiao Chen; Zixin Wang; Sen Wang; Zi Huang; Yadan Luo
ModSec-Learn: Boosting ModSecurity with Machine Learning. (2%)Christian Scano; Giuseppe Floris; Biagio Montaruli; Luca Demetrio; Andrea Valenza; Luca Compagna; Davide Ariu; Luca Piras; Davide Balzarotti; Battista Biggio
RobGC: Towards Robust Graph Condensation. (1%)Xinyi Gao; Hongzhi Yin; Tong Chen; Guanhua Ye; Wentao Zhang; Bin Cui
2024-06-18
Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation. (99%)Hetvi Waghela; Jaydip Sen; Sneha Rakshit
NoiSec: Harnessing Noise for Security against Adversarial and Backdoor Attacks. (97%)Md Hasan Shahriar; Ning Wang; Y. Thomas Hou; Wenjing Lou
MaskPure: Improving Defense Against Text Adversaries with Stochastic Purification. (95%)Harrison Gietz; Jugal Kalita
Adversarial Attacks on Multimodal Agents. (91%)Chen Henry Wu; Jing Yu Koh; Ruslan Salakhutdinov; Daniel Fried; Aditi Raghunathan
Towards Trustworthy Unsupervised Domain Adaptation: A Representation Learning Perspective for Enhancing Robustness, Discrimination, and Generalization. (76%)Jia-Li Yin; Haoyuan Zheng; Ximeng Liu
Adversarial Attacks on Large Language Models in Medicine. (70%)Yifan Yang; Qiao Jin; Furong Huang; Zhiyong Lu
Can Go AIs be adversarially robust? (61%)Tom Tseng; Euan McLean; Kellin Pelrine; Tony T. Wang; Adam Gleave
DLP: towards active defense against backdoor attacks with decoupled learning process. (31%)Zonghao Ying; Bin Wu
Attack and Defense of Deep Learning Models in the Field of Web Attack Detection. (10%)Lijia Shi; Shihao Dong
SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation. (10%)Xiaoze Liu; Ting Sun; Tianyang Xu; Feijie Wu; Cunxiang Wang; Xiaoqian Wang; Jing Gao
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models. (8%)Yuetai Li; Zhangchen Xu; Fengqing Jiang; Luyao Niu; Dinuka Sahabandu; Bhaskar Ramasubramanian; Radha Poovendran
Stealth edits for provably fixing or attacking large language models. (2%)Oliver J. Sutton; Qinghua Zhou; Wei Wang; Desmond J. Higham; Alexander N. Gorban; Alexander Bastounis; Ivan Y. Tyukin
PRePair: Pointwise Reasoning Enhance Pairwise Evaluating for Robust Instruction-Following Assessments. (1%)Hawon Jeong; ChaeHun Park; Jimin Hong; Jaegul Choo
2024-06-17
Obfuscating IoT Device Scanning Activity via Adversarial Example Generation. (99%)Haocong Li; Yaxin Zhang; Long Cheng; Wenjia Niu; Haining Wang; Qiang Li
FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks. (98%)Tobias Lorenz; Marta Kwiatkowska; Mario Fritz
Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness. (93%)Kejia Zhang; Juanjuan Weng; Junwei Wu; Guoqing Yang; Shaozi Li; Zhiming Luo
A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Driving. (82%)Yang Lou; Yi Zhu; Qun Song; Rui Tan; Chunming Qiao; Wei-Bin Lee; Jianping Wang
Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI. (76%)Robert Hönig; Javier Rando; Nicholas Carlini; Florian Tramèr
ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations. (22%)Yunze Xiao; Yujia Hu; Kenny Tsu Wei Choo; Roy Ka-wei Lee
Evading AI-Generated Content Detectors using Homoglyphs. (3%)Aldan Creo; Shushanta Pudasaini
BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning. (2%)Yi Liu; Cong Wang; Xingliang Yuan
SoK: A Literature and Engineering Review of Regular Expression Denial of Service. (2%)Masudul Hasan Masud Bhuiyan; Berk Çakar; Ethan H Burmane; James C Davis; Cristian-Alexandru Staicu
Do Parameters Reveal More than Loss for Membership Inference? (1%)Anshuman Suri; Xiao Zhang; David Evans
Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness. (1%)Maayan Ehrenberg; Roy Ganz; Nir Rosenfeld
2024-06-16
Improving Adversarial Robustness via Decoupled Visual Representation Masking. (99%)Decheng Liu; Tao Chen; Chunlei Peng; Nannan Wang; Ruimin Hu; Xinbo Gao
Imperceptible Face Forgery Attack via Adversarial Semantic Mask. (99%)Decheng Liu; Qixuan Su; Chunlei Peng; Nannan Wang; Xinbo Gao
KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs. (92%)Aihua Waseda University Pei; Zehua Waseda University Yang; Shunan Waseda University Zhu; Ruoxi Southeast University Cheng; Ju Southeast University Jia; Lina Wuhan University Wang
NBA: defensive distillation for backdoor removal via neural behavior alignment. (80%)Zonghao Ying; Bin Wu
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. (62%)Zhuoran Jin; Pengfei Cao; Chenhao Wang; Zhitao He; Hongbang Yuan; Jiachun Li; Yubo Chen; Kang Liu; Jun Zhao
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates. (61%)Fengqing Jiang; Zhangchen Xu; Luyao Niu; Bill Yuchen Lin; Radha Poovendran
Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition. (10%)Wenhan Yao; Jiangkun Yang; Yongqiang He; Jia Liu; Weiping Wen
RUPBench: Benchmarking Reasoning Under Perturbations for Robustness Evaluation in Large Language Models. (9%)Yuqing Wang; Yun Zhao
2024-06-15
Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networks. (98%)Nasrin Alipour; Seyyed Ali SeyyedSalehi
E-SAGE: Explainability-based Defense Against Backdoor Attacks on Graph Neural Networks. (81%)Dingqiang Yuan; Xiaohua Xu; Lei Yu; Tongchang Han; Rongchang Li; Meng Han
Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models. (68%)Rui Ye; Jingyi Chai; Xiangrui Liu; Yaodong Yang; Yanfeng Wang; Siheng Chen
Enhancing Anomaly Detection Generalization through Knowledge Exposure: The Dual Effects of Augmentation. (1%)Mohammad Akhavan Anvari; Rojina Kashefi; Vahid Reza Khazaie; Mohammad Khalooei; Mohammad Sabokrou
2024-06-14
Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis. (99%)Zhang Chen; Luca Demetrio; Srishti Gupta; Xiaoyi Feng; Zhaoqiang Xia; Antonio Emanuele Cinà; Maura Pintor; Luca Oneto; Ambra Demontis; Battista Biggio; Fabio Roli
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences. (93%)Saiyue Lyu; Shadab Shaikh; Frederick Shpilevskiy; Evan Shelhamer; Mathias Lécuyer
Robustness-Inspired Defense Against Backdoor Attacks on Graph Neural Networks. (75%)Zhiwei Zhang; Minhua Lin; Junjie Xu; Zongyu Wu; Enyan Dai; Suhang Wang
Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks. (67%)Matthias König; Xiyue Zhang; Holger H. Hoos; Marta Kwiatkowska; Rijn Jan N. van
Beyond Slow Signs in High-fidelity Model Extraction. (10%)Hanna Foerster; Robert Mullins; Ilia Shumailov; Jamie Hayes
Byzantine-Robust Decentralized Federated Learning. (8%)Minghong Fang; Zifan Zhang; Hairi; Prashant Khanduri; Jia Liu; Songtao Lu; Yuchen Liu; Neil Gong
2024-06-13
Improving Adversarial Robustness via Feature Pattern Consistency Constraint. (99%)Jiacong Hu; Jingwen Ye; Zunlei Feng; Jiazhen Yang; Shunyu Liu; Xiaotian Yu; Lingxiang Jia; Mingli Song
Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models. (98%)Changjiang Li; Ren Pang; Bochuan Cao; Jinghui Chen; Fenglong Ma; Shouling Ji; Ting Wang
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models. (95%)Samar Fares; Klea Ziu; Toluwani Aremu; Nikita Durasov; Martin Takáč; Pascal Fua; Karthik Nandakumar; Ivan Laptev
Towards Evaluating the Robustness of Visual State Space Models. (89%)Hashmat Shadab Malik; Fahad Shamshad; Muzammal Naseer; Karthik Nandakumar; Fahad Shahbaz Khan; Salman Khan
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. (11%)Zhao Xu; Fan Liu; Hao Liu
Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious? (4%)Pei Yang; Hai Ci; Yiren Song; Mike Zheng Shou
Validation of human benchmark models for Automated Driving System approval: How competent and careful are they really? (1%)Pierluigi Olleja; Gustav Markkula; Jonas Bärgman
An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records. (1%)Joakim Edin; Maria Maistro; Lars Maaløe; Lasse Borgholt; Jakob D. Havtorn; Tuukka Ruotsalo
Large-Scale Evaluation of Open-Set Image Classification Techniques. (1%)Halil Bisgin; Andres Palechor; Mike Suter; Manuel Günther
Understanding Hallucinations in Diffusion Models through Mode Interpolation. (1%)Sumukh K Aithal; Pratyush Maini; Zachary C. Lipton; J. Zico Kolter
2024-06-12
I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectors. (99%)Zijin Lin; Yue Zhao; Kai Chen; Jinwen He
On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models. (99%)Hashmat Shadab Malik; Numan Saeed; Asif Hanif; Muzammal Naseer; Mohammad Yaqub; Salman Khan; Fahad Shahbaz Khan
Adversarial Evasion Attack Efficiency against Large Language Models. (98%)João Vitorino; Eva Maia; Isabel Praça
Transformation-Dependent Adversarial Attacks. (89%)Yaoteng Tan; Zikui Cai; M. Salman Asif
When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search. (64%)Xuan Chen; Yuzhou Nie; Wenbo Guo; Xiangyu Zhang
RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs. (62%)Xuan Chen; Yuzhou Nie; Lu Yan; Yunshu Mao; Wenbo Guo; Xiangyu Zhang
AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer. (22%)Yitao Xu; Tong Zhang; Sabine Süsstrunk
Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attacks. (13%)Peizhi Niu; Chao Pan; Siheng Chen; Olgica Milenkovic
On Security Weaknesses and Vulnerabilities in Deep Learning Systems. (8%)Zhongzheng Lai; Huaming Chen; Ruoxi Sun; Yu Zhang; Minhui Xue; Dong Yuan
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition. (4%)Edoardo Debenedetti; Javier Rando; Daniel Paleka; Silaghi Fineas Florin; Dragos Albastroiu; Niv Cohen; Yuval Lemberg; Reshmi Ghosh; Rui Wen; Ahmed Salem; Giovanni Cherubin; Santiago Zanella-Beguelin; Robin Schmid; Victor Klemm; Takahiro Miki; Chenhao Li; Stefan Kraft; Mario Fritz; Florian Tramèr; Sahar Abdelnabi; Lea Schönherr
Improving Noise Robustness through Abstractions and its Impact on Machine Learning. (4%)Alfredo Personal Health Data Science, Sano - Centre for Computational Personalised Medicine Ibias; Karol Personal Health Data Science, Sano - Centre for Computational Personalised Medicine Capala; Varun Ravi Personal Health Data Science, Sano - Centre for Computational Personalised Medicine Varma; Anna Personal Health Data Science, Sano - Centre for Computational Personalised Medicine Drozdz; Jose Personal Health Data Science, Sano - Centre for Computational Personalised Medicine Sousa
Exploiting Uncommon Text-Encoded Structures for Automated Jailbreaks in LLMs. (1%)Bangxin Li; Hengrui Xing; Chao Huang; Jin Qian; Huangqing Xiao; Linfeng Feng; Cong Tian
Adversarial Patch for 3D Local Feature Extractor. (1%)Yu Wen Pao; Li Chang Lai; Hong-Yi Lin
2024-06-11
Erasing Radio Frequency Fingerprints via Active Adversarial Perturbation. (86%)Zhaoyi Lu; Wenchao Xu; Ming Tu; Xin Xie; Cunqing Hua; Nan Cheng
AudioMarkBench: Benchmarking Robustness of Audio Watermarking. (83%)Hongbin Liu; Moyang Guo; Zhengyuan Jiang; Lun Wang; Neil Zhenqiang Gong
On the H\"{o}lder Stability of Multiset and Graph Neural Networks. (69%)Yair Davidson; Nadav Dym
A Study of Backdoors in Instruction Fine-tuned Language Models. (31%)Jayaram Raghuram; George Kesidis; David J. Miller
Merging Improves Self-Critique Against Jailbreak Attacks. (26%)Victor Gallego
Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study. (15%)Yichi Zhang; Yao Huang; Yitong Sun; Chang Liu; Zhe Zhao; Zhengwei Fang; Yifan Wang; Huanran Chen; Xiao Yang; Xingxing Wei; Hang Su; Yinpeng Dong; Jun Zhu
Dual Thinking and Perceptual Analysis of Deep Learning Models using Human Adversarial Examples. (15%)Kailas Dayanandan; Anand Sinha; Brejesh Lall
MoreauPruner: Robust Pruning of Large Language Models against Weight Perturbations. (5%)Zixiao Wang; Jingwei Zhang; Wenqian Zhao; Farzan Farnia; Bei Yu
Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective. (1%)De Li; Xianxian Li; Zeming Gan; Qiyu Li; Bin Qu; Jinyan Wang
Agnostic Sharpness-Aware Minimization. (1%)Van-Anh Nguyen; Quyen Tran; Tuan Truong; Thanh-Toan Do; Dinh Phung; Trung Le
2024-06-10
Texture Re-scalable Universal Adversarial Perturbation. (99%)Yihao Huang; Qing Guo; Felix Juefei-Xu; Ming Hu; Xiaojun Jia; Xiaochun Cao; Geguang Pu; Yang Liu
Explainable Graph Neural Networks Under Fire. (99%)Zhong Li; Simon Geisler; Yuhang Wang; Stephan Günnemann; Leeuwen Matthijs van
Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning. (81%)Xiaoting Lyu; Yufei Han; Wei Wang; Jingkai Liu; Yongsheng Zhu; Guangquan Xu; Jiqiang Liu; Xiangliang Zhang
Reinforced Compressive Neural Architecture Search for Versatile Adversarial Robustness. (56%)Dingrong Wang; Hitesh Sapkota; Zhiqiang Tao; Qi Yu
Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications. (56%)Junlin Wang; Tianyi Yang; Roy Xie; Bhuwan Dhingra
A Survey of Backdoor Attacks and Defenses on Large Language Models: Implications for Security Measures. (13%)Shuai Zhao; Meihuizi Jia; Zhongliang Guo; Leilei Gan; Jie Fu; Yichao Feng; Fengjun Pan; Luu Anh Tuan
An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection. (8%)Shenao Yan; Shen Wang; Yue Duan; Hanbin Hong; Kiho Lee; Doowon Kim; Yuan Hong
Fast White-Box Adversarial Streaming Without a Random Oracle. (3%)Ying Feng; Aayush Jain; David P. Woodruff
Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks. (2%)Zonghao Ying; Aishan Liu; Xianglong Liu; Dacheng Tao
2024-06-09
DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks. (99%)Zhiyu Zhu; Jiayu Zhang; Xinyi Wang; Zhibo Jin; Huaming Chen
MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification. (97%)Sajjad Amini; Mohammadreza Teymoorianfard; Shiqing Ma; Amir Houmansadr
Stealthy Targeted Backdoor Attacks against Image Captioning. (82%)Wenshu Fan; Hongwei Li; Wenbo Jiang; Meng Hao; Shui Yu; Xiao Zhang
ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Driving. (80%)Chen Ma; Ningfei Wang; Zhengyu Zhao; Qian Wang; Qi Alfred Chen; Chao Shen
Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks. (67%)Zhiyuan Cheng; Cheng Han; James Liang; Qifan Wang; Xiangyu Zhang; Dongfang Liu
SlowPerception: Physical-World Latency Attack against Visual Perception in Autonomous Driving. (64%)Chen Ma; Ningfei Wang; Zhengyu Zhao; Qi Alfred Chen; Chao Shen
ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations. (38%)Sravanti Addepalli; Priyam Dey; R. Venkatesh Babu
Certified Robustness to Data Poisoning in Gradient-Based Training. (22%)Philip Sosnin; Mark N. Müller; Maximilian Baader; Calvin Tsay; Matthew Wicker
Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents. (4%)Avital Shafran; Roei Schuster; Vitaly Shmatikov
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection. (2%)Wei Li; Pin-Yu Chen; Sijia Liu; Ren Wang
A Relevance Model for Threat-Centric Ranking of Cybersecurity Vulnerabilities. (1%)Corren McCoy; Ross Gore; Michael L. Nelson; Michele C. Weigle
Safety Alignment Should Be Made More Than Just a Few Tokens Deep. (1%)Xiangyu Qi; Ashwinee Panda; Kaifeng Lyu; Xiao Ma; Subhrajit Roy; Ahmad Beirami; Prateek Mittal; Peter Henderson
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models. (1%)Alkis Kalavasis; Amin Karbasi; Argyris Oikonomou; Katerina Sotiraki; Grigoris Velegkas; Manolis Zampetakis
2024-06-08
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner. (99%)Xunguang Wang; Daoyuan Wu; Zhenlan Ji; Zongjie Li; Pingchuan Ma; Shuai Wang; Yingjiu Li; Yang Liu; Ning Liu; Juergen Rahmel
One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models. (99%)Hao Fang; Jiawei Kong; Wenbo Yu; Bin Chen; Jiawei Li; Shutao Xia; Ke Xu
Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization. (98%)Jiancong Xiao; Ruoyu Sun; Qi Long; Weijie J. Su
Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability. (96%)Junqi Gao; Biqing Qi; Yao Li; Zhichang Guo; Dong Li; Yuming Xing; Dazhi Zhang
Enhancing Adversarial Transferability via Information Bottleneck Constraints. (68%)Biqing Qi; Junqi Gao; Jianxing Liu; Ligang Wu; Bowen Zhou
Exploring Adversarial Robustness of Deep State Space Models. (56%)Biqing Qi; Yang Luo; Junqi Gao; Pengfei Li; Kai Tian; Zhiyuan Ma; Bowen Zhou
Adversarial flows: A gradient flow characterization of adversarial attacks. (13%)Lukas Weigand; Tim Roith; Martin Burger
2024-06-07
ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks. (99%)Feiyang Wang; Xingquan Zuo; Hai Huang; Gang Chen
Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning. (98%)Roman Belaire; Arunesh Sinha; Pradeep Varakantham
Corpus Poisoning via Approximate Greedy Gradient Descent. (86%)Jinyan Su; Preslav Nakov; Claire Cardie
Compositional Curvature Bounds for Deep Neural Networks. (84%)Taha Entesari; Sina Sharifi; Mahyar Fazlyab
Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs. (41%)Fan Liu; Zhao Xu; Hao Liu
Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness. (22%)Zahra Golpayegani; Patrick St-Amant; Nizar Bouguila
GENIE: Watermarking Graph Neural Networks for Link Prediction. (15%)Venkata Sai Pranav Bachina; Ankit Gangwal; Aaryan Ajay Sharma; Charu Sharma
The Price of Implicit Bias in Adversarially Robust Generalization. (5%)Nikolaos Tsilivis; Natalie Frank; Nathan Srebro; Julia Kempe
Contextual fusion enhances robustness to image blurring. (5%)Shruti Joshi; Aiswarya Akumalla; Seth Haney; Maxim Bazhenov
LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses. (1%)Weiran Lin; Anna Gerchanovsky; Omer Akgul; Lujo Bauer; Matt Fredrikson; Zifan Wang
2024-06-06
Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selection. (99%)Yinting School of Mathematics and Statistics, and Key Lab NAA--MOE, Central China Normal University Wu; Pai School of Mathematics and Computer Science, Jianghan University Peng; Bo Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, and School of Cyber Science and Engineering, Wuhan University Cai; Le School of Mathematics and Statistics, and Key Lab NAA--MOE, Central China Normal University Li; .
Talos: A More Effective and Efficient Adversarial Defense for GNN Models Based on the Global Homophily of Graphs. (98%)Duanyu Li; Huijun Wu; Min Xie; Xugang Wu; Zhenwei Wu; Wenzhe Zhang
Improving Alignment and Robustness with Circuit Breakers. (98%)Andy Zou; Long Phan; Justin Wang; Derek Duenas; Maxwell Lin; Maksym Andriushchenko; Rowan Wang; Zico Kolter; Matt Fredrikson; Dan Hendrycks
Behavior-Targeted Attack on Reinforcement Learning with Limited Access to Victim's Policy. (76%)Shojiro Yamabe; Kazuto Fukuchi; Ryoma Senda; Jun Sakuma
AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens. (69%)Lin Lu; Hai Yan; Zenghui Yuan; Jiawen Shi; Wenqi Wei; Pin-Yu Chen; Pan Zhou
Neural Codec-based Adversarial Sample Detection for Speaker Verification. (68%)Xuanjun Chen; Jiawei Du; Haibin Wu; Jyh-Shing Roger Jang; Hung-yi Lee
Interpreting the Second-Order Effects of Neurons in CLIP. (67%)Yossi Gandelsman; Alexei A. Efros; Jacob Steinhardt
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt. (56%)Zonghao Ying; Aishan Liu; Tianyuan Zhang; Zhengmin Yu; Siyuan Liang; Xianglong Liu; Dacheng Tao
Memorization in deep learning: A survey. (1%)Jiaheng Wei; Yanjun Zhang; Leo Yu Zhang; Ming Ding; Chao Chen; Kok-Leong Ong; Jun Zhang; Yang Xiang
2024-06-05
ZeroPur: Succinct Training-Free Adversarial Purification. (99%)Xiuli Bi; Zonglin Yang; Bo Liu; Xiaodong Cun; Chi-Man Pun; Pietro Lio; Bin Xiao
VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise. (99%)Zhixun He; Mukesh Singhal
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain. (99%)Jun Liu; Jiantao Zhou; Jiandian Zeng; Jinyu Tian; Zheng Li
Distributional Adversarial Loss. (96%)Saba Ahmadi; Siddharth Bhandari; Avrim Blum; Chen Dan; Prabhav Jain
Defending Large Language Models Against Attacks With Residual Stream Activation Analysis. (83%)Amelia Kawasaki; Andrew Davis; Houssam Abbas
Graph Neural Network Explanations are Fragile. (80%)Jiate Li; Meng Pang; Yun Dong; Jinyuan Jia; Binghui Wang
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models. (68%)Hamidreza Kamkari; Brendan Leigh Ross; Rasa Hosseinzadeh; Jesse C. Cresswell; Gabriel Loaiza-Ganem
Principles of Designing Robust Remote Face Anti-Spoofing Systems. (13%)Xiang Xu; Tianchen Zhao; Zheng Zhang; Zhihua Li; Jon Wu; Alessandro Achille; Mani Srivastava
Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders. (13%)Tingxu Han; Weisong Sun; Ziqi Ding; Chunrong Fang; Hanwei Qian; Jiaxun Li; Zhenyu Chen; Xiangyu Zhang
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits. (10%)Minzhou Pan; Yi Zeng; Xue Lin; Ning Yu; Cho-Jui Hsieh; Peter Henderson; Ruoxi Jia
Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections. (10%)Zihan Luo; Hong Huang; Yongkang Zhou; Jiping Zhang; Nuo Chen; Hai Jin
Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphs. (8%)Shuqi He; Jun Zhuang; Ding Wang; Luyao Peng; Jun Song
Reconstructing training data from document understanding models. (1%)Jérémie Dentan; Arnaud Paran; Aymen Shabou
FREA: Feasibility-Guided Generation of Safety-Critical Scenarios with Reasonable Adversariality. (1%)Keyu Chen; Yuheng Lei; Hao Cheng; Haoran Wu; Wenchao Sun; Sifa Zheng
2024-06-04
Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation. (99%)Yaohua Liu; Jiaxin Gao; Xuan Liu; Xianghao Jiao; Xin Fan; Risheng Liu
Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing. (98%)Youwei Shu; Xi Xiao; Derui Wang; Yuxin Cao; Siji Chen; Jason Xue; Linyi Li; Bo Li
PuFace: Defending against Facial Cloaking Attacks for Facial Recognition Models. (54%)Jing Wen
A Risk Estimation Study of Native Code Vulnerabilities in Android Applications. (5%)Silvia Lucia Sanna; Diego Soi; Davide Maiorca; Giorgio Fumera; Giorgio Giacinto
Verifying the Generalization of Deep Learning to Out-of-Distribution Domains. (3%)Guy Amir; Osher Maayan; Tom Zelazny; Guy Katz; Michael Schapira
Large Language Models as Carriers of Hidden Messages. (2%)Jakub Hoscilowicz; Pawel Popiolek; Jan Rudkowski; Jedrzej Bieniasz; Artur Janicki
Nonlinear Transformations Against Unlearnable Datasets. (2%)Thushari Hapuarachchi; Jing Lin; Kaiqi Xiong; Mohamed Rahouti; Gitte Ost
Inference Attacks: A Taxonomy, Survey, and Promising Directions. (1%)Feng Wu; Lei Cui; Shaowen Yao; Shui Yu
QROA: A Black-Box Query-Response Optimization Attack on LLMs. (1%)Hussein LaMME Jawad; Nicolas J. -B. LaMME BRUNEL
The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise. (1%)Yuanhao Ban; Ruochen Wang; Tianyi Zhou; Boqing Gong; Cho-Jui Hsieh; Minhao Cheng
Can Dense Connectivity Benefit Outlier Detection? An Odyssey with NAS. (1%)Hao Fu; Tunhou Zhang; Hai Li; Yiran Chen
2024-06-03
Constraint-based Adversarial Example Synthesis. (99%)Fang Yu; Ya-Yu Chi; Yu-Fang Chen
SVASTIN: Sparse Video Adversarial Attack via Spatio-Temporal Invertible Neural Networks. (99%)Yi Pan; Jun-Jie Huang; Zihan Chen; Wentao Zhao; Ziyue Wang
Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers. (93%)Fatemeh Nourilenjan Nokabadi; Jean-François Lalonde; Christian Gagné
CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models. (83%)Qian Lou; Xin Liang; Jiaqi Xue; Yancheng Zhang; Rui Xie; Mengxin Zheng
Are AI-Generated Text Detectors Robust to Adversarial Perturbations? (80%)Guanhua Huang; Yuchen Zhang; Zhe Li; Yongjian You; Mingze Wang; Zhouwang Yang
Model for Peanuts: Hijacking ML Models without Training Access is Possible. (62%)Mahmoud Ghorbel; Halima Bouzidi; Ioan Marius Bilasco; Ihsen Alouani
SLANT: Spurious Logo ANalysis Toolkit. (47%)Maan Qraitem; Piotr Teterwak; Kate Saenko; Bryan A. Plummer
MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering. (16%)Robert Osazuwa Ness; Katie Matton; Hayden Helm; Sheng Zhang; Junaid Bajwa; Carey E. Priebe; Eric Horvitz
From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation. (12%)Geraldin Nanfack; Michael Eickenberg; Eugene Belilovsky
A Game-Theoretic Approach to Privacy-Utility Tradeoff in Sharing Genomic Summary Statistics. (10%)Tao Zhang; Rajagopal Venkatesaramani; Rajat K. De; Bradley A. Malin; Yevgeniy Vorobeychik
Poisoning Attacks and Defenses in Recommender Systems: A Survey. (10%)Zongwei Wang; Junliang Yu; Min Gao; Wei Yuan; Guanhua Ye; Shazia Sadiq; Hongzhi Yin
Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits. (4%)Andis Draguns; Andrew Gritsevskiy; Sumeet Ramesh Motwani; Charlie Rogers-Smith; Jeffrey Ladish; Witt Christian Schroeder de
PRICE: A Pretrained Model for Cross-Database Cardinality Estimation. (1%)Tianjing Zeng; Junwei Lan; Jiahong Ma; Wenqing Wei; Rong Zhu; Pengfei Li; Bolin Ding; Defu Lian; Zhewei Wei; Jingren Zhou
2024-06-02
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data. (99%)Thibault Simonetto; Salah Ghamizi; Maxime Cordy
Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training. (98%)Jiacheng Zhang; Feng Liu; Dawei Zhou; Jingfeng Zhang; Tongliang Liu
A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder. (31%)Jingjing Zheng; Xin Yuan; Kai Li; Wei Ni; Eduardo Tovar; Jon Crowcroft
Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation. (13%)Yuan Xiao; Shiqing Ma; Juan Zhai; Chunrong Fang; Jinyuan Jia; Zhenyu Chen
Assessing the Adversarial Security of Perceptual Hashing Algorithms. (9%)Jordan Madden; Moxanki Bhavsar; Lhamo Dorje; Xiaohua Li
Invisible Backdoor Attacks on Diffusion Models. (2%)Sen Li; Junchi Ma; Minhao Cheng
2024-06-01
Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model. (3%)Jinyin Chen; Xiaoming Zhao; Haibin Zheng; Xiao Li; Sheng Xiang; Haifeng Guo
2024-05-31
Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks. (99%)Shaofei Li; Ziqi Zhang; Haomin Jia; Ding Li; Yao Guo; Xiangqun Chen
Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbations. (95%)Davide Coppola; Hwee Kuan Lee
Robust Stable Spiking Neural Networks. (38%)Jianhao Ding; Zhiyu Pan; Yujia Liu; Zhaofei Yu; Tiejun Huang
Improved Techniques for Optimization-Based Jailbreaking on Large Language Models. (26%)Xiaojun Jia; Tianyu Pang; Chao Du; Yihao Huang; Jindong Gu; Yang Liu; Xiaochun Cao; Min Lin
ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning. (22%)Zhangchen Xu; Fengqing Jiang; Luyao Niu; Jinyuan Jia; Bo Li; Radha Poovendran
Enhancing Jailbreak Attack Against Large Language Models through Silent Tokens. (13%)Jiahao Yu; Haozheng Luo; Jerry Yao-Chieh Hu; Wenbo Guo; Han Liu; Xinyu Xing
Exploring Vulnerabilities and Protections in Large Language Models: A Survey. (10%)Frank Weizhen Liu; Chenhui Hu
GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning. (9%)Xiaoyun Gan; Shanyu Gan; Taizhi Su; Peng Liu
Neural Network Verification with Branch-and-Bound for General Nonlinearities. (9%)Zhouxing Shi; Qirui Jin; Zico Kolter; Suman Jana; Cho-Jui Hsieh; Huan Zhang
StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization. (4%)Songhua Liu; Xin Jin; Xingyi Yang; Jingwen Ye; Xinchao Wang
GI-NAS: Boosting Gradient Inversion Attacks through Adaptive Neural Architecture Search. (1%)Wenbo Yu; Hao Fang; Bin Chen; Xiaohang Sui; Chuan Chen; Hao Wu; Shu-Tao Xia; Ke Xu
2024-05-30
Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization. (99%)Yisu Liu; Jinyang An; Wanqian Zhang; Dayan Wu; Jingzi Gu; Zheng Lin; Weiping Wang
HOLMES: to Detect Adversarial Examples with Multiple Detectors. (99%)Jing Wen
Typography Leads Semantic Diversifying: Amplifying Adversarial Transferability across Multimodal Large Language Models. (99%)Hao Cheng; Erjia Xiao; Jiayan Yang; Jiahang Cao; Qiang Zhang; Le Yang; Jize Zhang; Kaidi Xu; Jindong Gu; Renjing Xu
Enhancing Adversarial Robustness in SNNs with Sparse Gradients. (92%)Yujia Liu; Tong Bu; Jianhao Ding; Zecheng Hao; Tiejun Huang; Zhaofei Yu
Exploring the Robustness of Decision-Level Through Adversarial Attacks on LLM-Based Embodied Models. (89%)Shuyuan Liu; Jiawei Chen; Shouwei Ruan; Hang Su; Zhaoxia Yin
Phantom: General Trigger Attacks on Retrieval Augmented Language Generation. (83%)Harsh Chaudhari; Giorgio Severi; John Abascal; Matthew Jagielski; Christopher A. Choquette-Choo; Milad Nasr; Cristina Nita-Rotaru; Alina Oprea
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents. (75%)Ethan Rathbun; Christopher Amato; Alina Oprea
Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networks. (73%)Sylvia Worlali Azumah; Nelly Elsayed; Zag ElSayed; Murat Ozer; Guardia Amanda La
BAN: Detecting Backdoors Activated by Adversarial Neuron Noise. (68%)Xiaoyun Xu; Zhuoran Liu; Stefanos Koffas; Shujian Yu; Stjepan Picek
Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation. (45%)Maya Anderson; Guy Amit; Abigail Goldsteen
Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks. (38%)Chen Xiong; Xiangyu Qi; Pin-Yu Chen; Tsung-Yi Ho
Large Language Model Watermark Stealing With Mixed Integer Programming. (33%)Zhaoxi Zhang; Xiaomei Zhang; Yanjun Zhang; Leo Yu Zhang; Chao Chen; Shengshan Hu; Asif Gill; Shirui Pan
DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-World. (22%)Wenli Sun; Xinyang Jiang; Dongsheng Li; Cairong Zhao
Investigating the Robustness of LLMs on Math Word Problems. (16%)Ujjwala Anantheswaran; Himanshu Gupta; Kevin Scaria; Shreyas Verma; Chitta Baral; Swaroop Mishra
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness. (5%)Weilin Lin; Li Liu; Shaokui Wei; Jianze Li; Hui Xiong
Certifying Global Robustness for Deep Neural Networks. (2%)You Li; Guannan Zhao; Shuyu Kong; Yunqi He; Hai Zhou
Breaking Indistinguishability with Transfer Learning: A First Look at SPECK32/64 Lightweight Block Ciphers. (1%)Jimmy Dani; Kalyan Nakka; Nitesh Saxena
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable. (1%)Martin Bertran; Shuai Tang; Michael Kearns; Jamie Morgenstern; Aaron Roth; Zhiwei Steven Wu
2024-05-29
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior. (99%)Shuyu Cheng; Yibo Miao; Yinpeng Dong; Xiao Yang; Xiao-Shan Gao; Jun Zhu
Leveraging Many-To-Many Relationships for Defending Against Visual-Language Adversarial Attacks. (96%)Futa Waseda; Antonio Tejero-de-Pablos
Model Agnostic Defense against Adversarial Patch Attacks on Object Detection in Unmanned Aerial Vehicles. (92%)Saurabh Pathak; Samridha Shrestha; Abdelrahman AlMahmoud
Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies. (92%)Yipu Chen; Haotian Xue; Yongxin Chen
Evaluating the Effectiveness and Robustness of Visual Similarity-based Phishing Detection Models. (91%)Fujiao Ji; Kiho Lee; Hyungjoon Koo; Wenhao You; Euijin Choo; Hyoungshick Kim; Doowon Kim
Verifiably Robust Conformal Prediction. (82%)Linus Jeary; Tom Kuipers; Mehran Hosseini; Nicola Paoletti
AI Risk Management Should Incorporate Both Safety and Security. (67%)Xiangyu Qi; Yangsibo Huang; Yi Zeng; Edoardo Debenedetti; Jonas Geiping; Luxi He; Kaixuan Huang; Udari Madhushani; Vikash Sehwag; Weijia Shi; Boyi Wei; Tinghao Xie; Danqi Chen; Pin-Yu Chen; Jeffrey Ding; Ruoxi Jia; Jiaqi Ma; Arvind Narayanan; Weijie J Su; Mengdi Wang; Chaowei Xiao; Bo Li; Dawn Song; Peter Henderson; Prateek Mittal
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization. (61%)Jiawei Chen; Xiao Yang; Zhengwei Fang; Yu Tian; Yinpeng Dong; Zhaoxia Yin; Hang Su
EntProp: High Entropy Propagation for Improving Accuracy and Robustness. (50%)Shohei Enomoto
ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning. (26%)Ruchika Chavhan; Da Li; Timothy Hospedales
Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning. (22%)Dipam Goswami; Albin Soutif--Cormerais; Yuyang Liu; Sandesh Kamath; Bartłomiej Twardowski; de Weijer Joost van
Node Injection Attack Based on Label Propagation Against Graph Neural Network. (12%)Peican Zhu; Zechen Pan; Keke Tang; Xiaodong Cui; Jinhuan Wang; Qi Xuan
Genshin: General Shield for Natural Language Processing with Large Language Models. (5%)Xiao Peng; Tao Liu; Ying Wang
Confronting the Reproducibility Crisis: A Case Study of Challenges in Cybersecurity AI. (2%)Richard H. Moulton; Gary A. McCully; John D. Hastings
Enhancing Security and Privacy in Federated Learning using Update Digests and Voting-Based Defense. (1%)Wenjie Li; Kai Fan; Jingyuan Zhang; Hui Li; Wei Yang Bryan Lim; Qiang Yang
Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning. (1%)Keltin Grimes; Collin Abidi; Cole Frank; Shannon Gallagher
MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection. (1%)Raman Dutt; Ondrej Bohdal; Pedro Sanchez; Sotirios A. Tsaftaris; Timothy Hospedales
2024-05-28
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks. (99%)Zhenxing Niu; Yuyao Sun; Qiguang Miao; Rong Jin; Gang Hua
Improved Generation of Adversarial Examples Against Safety-aligned LLMs. (99%)Qizhang Li; Yiwen Guo; Wangmeng Zuo; Hao Chen
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics. (98%)Sunay Bhat; Jeffrey Jiang; Omead Pooladzandi; Alexander Branch; Gregory Pottie
PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models. (98%)Omead Pooladzandi; Jeffrey Jiang; Sunay Bhat; Gregory Pottie
White-box Multimodal Jailbreaks Against Large Vision-Language Models. (96%)Ruofan Wang; Xingjun Ma; Hanxu Zhou; Chuanjun Ji; Guangnan Ye; Yu-Gang Jiang
Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing. (92%)Wei Zhao; Zhe Li; Yige Li; Ye Zhang; Jun Sun
Wavelet-Based Image Tokenizer for Vision Transformers. (64%)Zhenhai Zhu; Radu Soricut
Cross-Context Backdoor Attacks against Graph Prompt Learning. (13%)Xiaoting Lyu; Yufei Han; Wei Wang; Hangwei Qian; Ivor Tsang; Xiangliang Zhang
BlueSWAT: A Lightweight State-Aware Security Framework for Bluetooth Low Energy. (1%)Xijia Che; Yi He; Xuewei Feng; Kun Sun; Ke Xu; Qi Li
Watermarking Counterfactual Explanations. (1%)Hangzhi Guo; Firdaus Ahmed Choudhury; Tinghua Chen; Amulya Yadav
Black-Box Detection of Language Model Watermarks. (1%)Thibaud Gloaguen; Nikola Jovanović; Robin Staab; Martin Vechev
2024-05-27
Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models. (99%)Fengfan Zhou; Qianyu Zhou; Xiangtai Li; Xuequan Lu; Lizhuang Ma; Hefei Ling
The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective. (99%)Nils Philipp Walter; Linara Adilova; Jilles Vreeken; Michael Kamp
Exploiting the Layered Intrinsic Dimensionality of Deep Models for Practical Adversarial Training. (98%)Enes Altinisik; Safa Messaoud; Husrev Taha Sencar; Hassan Sajjad; Sanjay Chawla
Spectral regularization for adversarially-robust representation learning. (86%)Sheng Yang; Jacob A. Zavatone-Veth; Cengiz Pehlevan
TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability. (83%)Fengji Ma; Li Liu; Hei Victor Cheng
OSLO: One-Shot Label-Only Membership Inference Attacks. (81%)Yuefeng Peng; Jaechul Roh; Subhransu Maji; Amir Houmansadr
Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization. (33%)Jianting Yang; Srećko Ðurašinović; Jean-Bernard Lasserre; Victor Magron; Jun Zhao
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective. (26%)Nan Li; Haiyang Yu; Ping Yi
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models. (8%)ShengYun Peng; Pin-Yu Chen; Matthew Hull; Duen Horng Chau
Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems. (5%)Ruochen Jiao; Shaoyuan Xie; Justin Yue; Takami Sato; Lixu Wang; Yixuan Wang; Qi Alfred Chen; Qi Zhu
LabObf: A Label Protection Scheme for Vertical Federated Learning Through Label Obfuscation. (1%)Ying He; Mingyang Niu; Jingyu Hua; Yunlong Mao; Xu Huang; Chen Li; Sheng Zhong
Magnitude-based Neuron Pruning for Backdoor Defens. (1%)Nan Li; Haoyu Jiang; Ping Yi
2024-05-26
Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models. (67%)Xijie Huang; Xinyuan Wang; Hantao Zhang; Yinghao Zhu; Jiawen Xi; Jingkun An; Hao Wang; Hao Liang; Chengwei Pan
Pruning for Robust Concept Erasing in Diffusion Models. (38%)Tianyun Yang; Juan Cao; Chang Xu
TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models. (31%)Yuzhou. Nie; Yanting. Wang; Jinyuan. Jia; Lucia Michael J. De; Nathaniel D. Bastian; Wenbo. Guo; Dawn. Song
Partial train and isolate, mitigate backdoor attack. (1%)Yong Li; Han Gao
Automatic Jailbreaking of the Text-to-Image Generative AI Systems. (1%)Minseon Kim; Hyomin Lee; Boqing Gong; Huishuai Zhang; Sung Ju Hwang
2024-05-25
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack. (99%)Mingli Zhu; Siyuan Liang; Baoyuan Wu
Detecting Adversarial Data via Perturbation Forgery. (99%)Qian Wang; Chen Li; Yuchen Luo; Hefei Ling; Ping Li; Jiazhong Chen; Shijuan Huang; Ning Yu
Enhancing Adversarial Transferability Through Neighborhood Conditional Sampling. (98%)Chunlin Qiu; Yiheng Duan; Lingchen Zhao; Qian Wang
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model. (97%)Changhoon Kim; Kyle Min; Yezhou Yang
Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets. (89%)Hyekyoung Hwang; Jitae Shin
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency. (81%)Runqi Lin; Chaojian Yu; Bo Han; Hang Su; Tongliang Liu
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor. (70%)Shaokui Wei; Hongyuan Zha; Baoyuan Wu
Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character. (56%)Siyuan Ma; Weidi Luo; Yu Wang; Xiaogeng Liu
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level. (8%)Runlin Lei; Yuwei Hu; Yuchen Ren; Zhewei Wei
No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks. (4%)Chak Tou Leong; Yi Cheng; Kaishuai Xu; Jian Wang; Hanlin Wang; Wenjie Li
Robust Message Embedding via Attention Flow-Based Steganography. (1%)Huayuan Ye; Shenzhuo Zhang; Shiqi Jiang; Jing Liao; Shuhang Gu; Dejun Zheng; Changbo Wang; Chenhui Li
2024-05-24
Robust width: A lightweight and certifiable adversarial defense. (99%)Jonathan Peck; Bart Goossens
Large Language Model Sentinel: LLM Agent for Adversarial Purification. (99%)Guang Lin; Qibin Zhao
Adversarial Attacks on Hidden Tasks in Multi-Task Learning. (98%)Yu Zhe; Rei Nagaike; Daiki Nishiyama; Kazuto Fukuchi; Jun Sakuma
Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning. (95%)Simon Yu; Jie He; Pasquale Minervini; Jeff Z. Pan
Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness. (92%)Jieren Deng; Hanbin Hong; Aaron Palmer; Xin Zhou; Jinbo Bi; Kaleel Mahmood; Yuan Hong; Derek Aguiar
Efficient Adversarial Training in LLMs with Continuous Attacks. (92%)Sophie Xhonneux; Alessandro Sordoni; Stephan Günnemann; Gauthier Gidel; Leo Schwinn
Rethinking Independent Cross-Entropy Loss For Graph-Structured Data. (76%)Rui Miao; Kaixiong Zhou; Yili Wang; Ninghao Liu; Ying Wang; Xin Wang
BDetCLIP: Multimodal Prompting Contrastive Test-Time Backdoor Detection. (61%)Yuwei Niu; Shuo He; Qi Wei; Zongyu Wu; Feng Liu; Lei Feng
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models. (47%)Yimeng Zhang; Xin Chen; Jinghan Jia; Yihua Zhang; Chongyu Fan; Jiancheng Liu; Mingyi Hong; Ke Ding; Sijia Liu
Robustifying Safety-Aligned Large Language Models through Clean Data Curation. (15%)Xiaoqun Liu; Jiacheng Liang; Muchao Ye; Zhaohan Xi
HiddenSpeaker: Generate Imperceptible Unlearnable Audios for Speaker Verification System. (15%)Zhisheng Zhang; Pengyang Huang
Can Implicit Bias Imply Adversarial Robustness? (11%)Hancheng Min; René Vidal
Certifiably Robust RAG against Retrieval Corruption. (10%)Chong Xiang; Tong Wu; Zexuan Zhong; David Wagner; Danqi Chen; Prateek Mittal
BadGD: A unified data-centric framework to identify gradient descent vulnerabilities. (8%)Chi-Hua Wang; Guang Cheng
AuthNet: Neural Network with Integrated Authentication Logic. (5%)Yuling Cai; Fan Xiang; Guozhu Meng; Yinzhi Cao; Kai Chen
Revisit, Extend, and Enhance Hessian-Free Influence Functions. (2%)Ziao Yang; Han Yue; Jian Chen; Hongfu Liu
2024-05-23
Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds. (98%)Hanwei Zhang; Luo Cheng; Qisong He; Wei Huang; Renjue Li; Ronan Sicre; Xiaowei Huang; Holger Hermanns; Lijun Zhang
Certified Robustness against Sparse Adversarial Perturbations via Data Localization. (92%)Ambar Pal; René Vidal; Jeremias Sulam
A New Formulation for Zeroth-Order Optimization of Adversarial EXEmples in Malware Detection. (91%)Marco Rando; Luca Demetrio; Lorenzo Rosasco; Fabio Roli
Generating camera failures as a class of physics-based adversarial examples. (87%)Manav Prabhakar; Jwalandhar Girnar; Arpan Kusari
TrojanForge: Generating Adversarial Hardware Trojan Examples with Reinforcement Learning. (84%)Amin Sarihi; Peter Jamieson; Ahmad Patooghy; Abdel-Hameed A. Badawy
Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography. (83%)Nhat Chung; Sensen Gao; Tuan-Anh Vu; Jie Zhang; Aishan Liu; Yun Lin; Jin Song Dong; Qing Guo
SLIFER: Investigating Performance and Robustness of Malware Detection Pipelines. (81%)Andrea Ponte; Dmitrijs Trizna; Luca Demetrio; Battista Biggio; Ivan Tesfai Ogbu; Fabio Roli
How Does Bayes Error Limit Probabilistic Robust Accuracy. (76%)Ruihan Zhang; Jun Sun
Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution. (67%)Zakariya Chaouai; Mohamed Tamaazousti
Towards Imperceptible Backdoor Attack in Self-supervised Learning. (61%)Hanrong Zhang; Zhenting Wang; Tingxu Han; Mingyu Jin; Chenlu Zhan; Mengnan Du; Hongwei Wang; Shiqing Ma
Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models. (33%)Yiming Chen; Chen Zhang; Danqing Luo; Luis Fernando D'Haro; Robby T. Tan; Haizhou Li
AdjointDEIS: Efficient Gradients for Diffusion Models. (15%)Zander W. Blasingame; Chen Liu
What Variables Affect Out-of-Distribution Generalization in Pretrained Models? (9%)Md Yousuf Harun; Kyungbok Lee; Jhair Gallardo; Giri Krishnan; Christopher Kanan
Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model. (8%)Tudor Cebere; Aurélien Bellet; Nicolas Papernot
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation. (1%)Peihua Mai; Ran Yan; Yan Pang
Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark. (1%)Huali Ren; Anli Yan; Chong-zhi Gao; Hongyang Yan; Zhenxin Zhang; Jin Li
2024-05-22
Learning to Transform Dynamically for Better Adversarial Transferability. (99%)Rongyi Zhu; Zeliang Zhang; Susan Liang; Zhuo Liu; Chenliang Xu
Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization. (80%)Daniel Kuelbs; Sanjay Lall; Mert Pilanci
Towards Certification of Uncertainty Calibration under Adversarial Attacks. (75%)Cornelius Emde; Francesco Pinto; Thomas Lukasiewicz; Philip H. S. Torr; Adel Bibi
LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate. (67%)Anthony Fuller; Daniel G. Kyrollos; Yousef Yassin; James R. Green
Remote Keylogging Attacks in Multi-user VR Applications. (13%)Zihao Su; Kunlin Cai; Reuben Beeler; Lukas Dresel; Allan Garcia; Ilya Grishchenko; Yuan Tian; Christopher Kruegel; Giovanni Vigna
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning. (5%)Meenatchi Sundaram Muthu Selva Annamalai; Cristofaro Emiliano De
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response. (1%)Tianrong Zhang; Bochuan Cao; Yuanpu Cao; Lu Lin; Prasenjit Mitra; Jinghui Chen
2024-05-21
Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data. (92%)Yuwen Pu; Jiahao Chen; Chunyi Zhou; Zhou Feng; Qingming Li; Chunqiang Hu; Shouling Ji
Adversarial Training via Adaptive Knowledge Amalgamation of an Ensemble of Teachers. (87%)Shayan Mohajer Hamidi; Linfeng Ye
Rethinking the Vulnerabilities of Face Recognition Systems:From a Practical Perspective. (78%)Jiahao Chen; Zhiqiang Shen; Yuwen Pu; Chunyi Zhou; Shouling Ji
EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection. (47%)Yuwen Qian; Shuchi Wu; Kang Wei; Ming Ding; Di Xiao; Tao Xiang; Chuan Ma; Song Guo
Fully Randomized Pointers. (15%)Gregory J. Duck; Sai Dhawal Phaye; Roland H. C. Yap; Trevor E. Carlson
A novel reliability attack of Physical Unclonable Functions. (13%)Gaoxiang Li; Yu Zhuang
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks. (8%)Boheng Li; Yishuo Cai; Haowei Li; Feng Xue; Zhifeng Li; Yiming Li
Dullahan: Stealthy Backdoor Attack against Without-Label-Sharing Split Learning. (4%)Yuwen Pu; Zhuoyuan Ding; Jiahao Chen; Chunyi Zhou; Qingming Li; Chunqiang Hu; Shouling Ji
Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming. (1%)Jiaxu Liu; Xiangyu Yin; Sihao Wu; Jianhong Wang; Meng Fang; Xinping Yi; Xiaowei Huang
2024-05-20
A Constraint-Enforcing Reward for Adversarial Attacks on Text Classifiers. (99%)Tom Roth; Inigo Jauregi Unanue; Alsharif Abuadbba; Massimo Piccardi
GAN-GRID: A Novel Generative Attack on Smart Grid Stability Prediction. (98%)Emad Efatinasab; Alessandro Brighente; Mirco Rampazzo; Nahal Azadi; Mauro Conti
Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space. (76%)Qianmei Liu; Yufei Kuang; Jie Wang
EGAN: Evolutional GAN for Ransomware Evasion. (74%)Daniel Commey; Benjamin Appiah; Bill K. Frimpong; Isaac Osei; Ebenezer N. A. Hammond; Garth V. Crosby
Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers. (31%)Fan Shi; Chong Zhang; Takahiro Miki; Joonho Lee; Marco Hutter; Stelian Coros
Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning. (8%)Hikmat Khan; Ghulam Rasool; Nidhal Carla Bouaynaya
Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks. (3%)Marcin Podhajski; Jan Dubiński; Franziska Boenisch; Adam Dziedzic; Agnieszka Pregowska; Tomasz Michalak
DispaRisk: Auditing Fairness Through Usable Information. (1%)Jonathan Vasquez; Carlotta Domeniconi; Huzefa Rangwala
2024-05-19
Adaptive Batch Normalization Networks for Adversarial Robustness. (99%)Shao-Yuan Lo; Vishal M. Patel
An Invisible Backdoor Attack Based On Semantic Feature. (96%)Yangming Chen
Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors. (81%)Ruihan Zhang; Jun Sun
A GAN-Based Data Poisoning Attack Against Federated Learning Systems and Its Countermeasure. (68%)Wei Sun; Bo Gao; Ke Xiong; Yuwei Wang
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks. (62%)Xuanli He; Qiongkai Xu; Jun Wang; Benjamin I. P. Rubinstein; Trevor Cohn
Fed-Credit: Robust Federated Learning with Credibility Management. (13%)Jiayan Chen; Zhirong Qian; Tianhui Meng; Xitong Gao; Tian Wang; Weijia Jia
BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution. (5%)Jun Wang; Benedetta Tondi; Mauro Barni
2024-05-18
Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses. (84%)Thanh Nguyen; Tung M. Luu; Tri Ton; Chang D. Yoo
Trustworthy Actionable Perturbations. (82%)Jesse Friedbaum; Sudarshan Adiga; Ravi Tandon
Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing. (13%)Yunlong Zhao; Xiaoheng Deng; Yijing Liu; Xinjun Pei; Jiazhi Xia; Wei Chen
UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers. (12%)Duo Peng; Qiuhong Ke; Jun Liu
BadActs: A Universal Backdoor Defense in the Activation Space. (10%)Biao Yi; Sishuo Chen; Yiming Li; Tong Li; Baolei Zhang; Zheli Liu
On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks. (8%)Nicholas H. Barbara; Ruigang Wang; Ian R. Manchester
Diffusion Model Driven Test-Time Image Adaptation for Robust Skin Lesion Classification. (3%)Ming Hu; Siyuan Yan; Peng Xia; Feilong Tang; Wenxue Li; Peibo Duan; Lin Zhang; Zongyuan Ge
2024-05-17
Revisiting the Robust Generalization of Adversarial Prompt Tuning. (99%)Fan Yang; Mingxuan Xia; Sangzhou Xia; Chicheng Ma; Hui Hui
Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors. (99%)Jiachen Sun; Changsheng Wang; Jiongxiao Wang; Yiwei Zhang; Chaowei Xiao
Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective. (83%)Zhiwei Zhang; Minhua Lin; Enyan Dai; Suhang Wang
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers. (67%)Sheng Yang; Jiawang Bai; Kuofeng Gao; Yong Yang; Yiming Li; Shu-tao Xia
Boosting Few-Pixel Robustness Verification via Covering Verification Designs. (1%)Yuval Shapira; Naor Wiesel; Shahar Shabelman; Dana Drachsler-Cohen
2024-05-16
DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection. (99%)Yuhao Sun; Lingyun Yu; Hongtao Xie; Jiaming Li; Yongdong Zhang
Infrared Adversarial Car Stickers. (98%)Xiaopei Zhu; Yuqiu Liu; Zhanhao Hu; Jianmin Li; Xiaolin Hu
Adversarial Robustness for Visual Grounding of Multimodal Large Language Models. (95%)Kuofeng Gao; Yang Bai; Jiawang Bai; Yong Yang; Shu-Tao Xia
Adversarial Robustness Guarantees for Quantum Classifiers. (81%)Neil Dowling; Maxwell T. West; Angus Southwell; Azar C. Nakhl; Martin Sevior; Muhammad Usman; Kavan Modi
Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks. (13%)Haonan An; Guang Hua; Zhiping Lin; Yuguang Fang
Relational DNN Verification With Cross Executional Bound Refinement. (8%)Debangshu Banerjee; Gagandeep Singh
Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution. (1%)Eslam Zaher; Maciej Trzaskowski; Quan Nguyen; Fred Roosta
Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomy. (1%)Yichuan Shi; Olivera Kotevska; Viktor Reshniak; Abhishek Singh; Ramesh Raskar
2024-05-15
Properties that allow or prohibit transferability of adversarial attacks among quantized networks. (99%)Abhishek Shrestha; Jürgen Großmann
Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer. (99%)Weifei Jin; Yuxin Cao; Junjie Su; Qi Shen; Kai Ye; Derui Wang; Jie Hao; Ziyao Liu
Cross-Input Certified Training for Universal Perturbations. (98%)Changming Xu; Gagandeep Singh
IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency. (4%)Linshan Hou; Ruili Feng; Zhongyun Hua; Wei Luo; Leo Yu Zhang; Yiming Li
Themis: Automatic and Efficient Deep Learning System Testing with Strong Fault Detection Capability. (4%)Tsz On Li; Dong Huang; Xiaofei Xie; Heming Cui
Optimizing Sensor Network Design for Multiple Coverage. (1%)Lukas Taus; Yen-Hsi Richard Tsai
2024-05-14
SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models. (99%)Raghuveer Peri; Sai Muralidhar Jayanthi; Srikanth Ronanki; Anshu Bhatia; Karel Mundnich; Saket Dingliwal; Nilaksh Das; Zejiang Hou; Goeric Huybrechts; Srikanth Vishnubhotla; Daniel Garcia-Romero; Sundararajan Srinivasan; Kyu J Han; Katrin Kirchhoff
Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretation. (92%)Boqi Chen; Kristóf Marussy; Oszkár Semeráth; Gunter Mussbacher; Dániel Varró
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks. (92%)Ziquan Liu; Yufei Cui; Yan Yan; Yi Xu; Xiangyang Ji; Xue Liu; Antoni B. Chan
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition. (11%)Lingdong Kong; Shaoyuan Xie; Hanjiang Hu; Yaru Niu; Wei Tsang Ooi; Benoit R. Cottereau; Lai Xing Ng; Yuexin Ma; Wenwei Zhang; Liang Pan; Kai Chen; Ziwei Liu; Weichao Qiu; Wei Zhang; Xu Cao; Hao Lu; Ying-Cong Chen; Caixin Kang; Xinning Zhou; Chengyang Ying; Wentao Shang; Xingxing Wei; Yinpeng Dong; Bo Yang; Shengyin Jiang; Zeliang Ma; Dengyi Ji; Haiwen Li; Xingliang Huang; Yu Tian; Genghua Kou; Fan Jia; Yingfei Liu; Tiancai Wang; Ying Li; Xiaoshuai Hao; Yifan Yang; Hui Zhang; Mengchuan Wei; Yi Zhou; Haimei Zhao; Jing Zhang; Jinke Li; Xiao He; Xiaoqiang Cheng; Bingyang Zhang; Lirong Zhao; Dianlei Ding; Fangsheng Liu; Yixiang Yan; Hongming Wang; Nanfei Ye; Lun Luo; Yubo Tian; Yiwei Zuo; Zhe Cao; Yi Ren; Yunfan Li; Wenjie Liu; Xun Wu; Yifan Mao; Ming Li; Jian Liu; Jiayang Liu; Zihan Qin; Cunxi Chu; Jialei Xu; Wenbo Zhao; Junjun Jiang; Xianming Liu; Ziyan Wang; Chiwei Li; Shilong Li; Chendong Yuan; Songyue Yang; Wentao Liu; Peng Chen; Bin Zhou; Yubo Wang; Chi Zhang; Jianhang Sun; Hai Chen; Xiao Yang; Lizhong Wang; Dongyi Fu; Yongchun Lin; Huitong Yang; Haoang Li; Yadan Luo; Xianjing Cheng; Yong Xu
Pointwise Lipschitz Continuous Graph Algorithms via Proximal Gradient Analysis. (1%)Quanquan C. Liu; Grigoris Velegkas; Yuichi Yoshida; Felix Zhou
Achieving Resolution-Agnostic DNN-based Image Watermarking:A Novel Perspective of Implicit Neural Representation. (1%)Yuchen Wang; Xingyu Zhu; Guanhui Ye; Shiyao Zhang; Xuetao Wei
Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning. (1%)Chendi Wang; Yuqing Zhu; Weijie J. Su; Yu-Xiang Wang
UnMarker: A Universal Attack on Defensive Watermarking. (1%)Andre Kassis; Urs Hengartner
RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing. (1%)Aref Miri Rekavandi; Olga Ohrimenko; Benjamin I. P. Rubinstein
2024-05-13
Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection. (96%)Dehong Kong; Siyuan Liang; Wenqi Ren
CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models. (82%)Qilin Zhou; Zhengyuan Wei; Haipeng Wang; Bo Jiang; W. K. Chan
RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors. (15%)Liam Dugan; Alyssa Hwang; Filip Trhlik; Josh Magnus Ludan; Andrew Zhu; Hainiu Xu; Daphne Ippolito; Chris Callison-Burch
GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation. (11%)Andrey V. Galichin; Mikhail Pautov; Alexey Zhavoronkin; Oleg Y. Rogov; Ivan Oseledets
Backdoor Removal for Generative Large Language Models. (1%)Haoran Li; Yulin Chen; Zihao Zheng; Qi Hu; Chunkit Chan; Heshan Liu; Yangqiu Song
2024-05-11
Stealthy Imitation: Reward-guided Environment-free Policy Stealing. (1%)Zhixiong Zhuang; Maria-Irina Nicolae; Mario Fritz
2024-05-10
Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing. (99%)Juanjuan Weng; Zhiming Luo; Shaozi Li
Disttack: Graph Adversarial Attacks Toward Distributed GNN Training. (98%)Yuxiang Zhang; Xin Liu; Meng Wu; Wei Yan; Mingyu Yan; Xiaochun Ye; Dongrui Fan
Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach. (98%)Amira Guesmi; Nishant Suresh Aswani; Muhammad Shafique
Evaluating Adversarial Robustness in the Spatial Frequency Domain. (96%)Keng-Hsin Liao; Chin-Yuan Yeh; Hsi-Wen Chen; Ming-Syan Chen
Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions. (96%)Fan Wang; Adams Wai-Kin Kong
PUMA: margin-based data pruning. (80%)Javier Maroto; Pascal Frossard
2024-05-09
BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization. (99%)Satyadwyoom Kumar; Saurabh Gupta; Arun Balaji Buduru
Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models. (97%)Vyas Raina; Rao Ma; Charles McGhee; Kate Knill; Mark Gales
Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers. (80%)Binxiao Huang; Jason Chun Lok; Chang Liu; Ngai Wong
Link Stealing Attacks Against Inductive Graph Neural Networks. (75%)Yixin Wu; Xinlei He; Pascal Berrang; Mathias Humbert; Michael Backes; Neil Zhenqiang Gong; Yang Zhang
Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search. (68%)Zachary Coalson; Huazheng Wang; Qingyun Wu; Sanghyun Hong
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning. (62%)Yujie Zhang; Neil Gong; Michael K. Reiter
Towards Robust Physical-world Backdoor Attacks on Lane Detection. (50%)Xinwei Zhang; Aishan Liu; Tianyuan Zhang; Siyuan Liang; Xianglong Liu
Model Inversion Robustness: Can Transfer Learning Help? (45%)Sy-Tuyen Ho; Koh Jun Hao; Keshigeyan Chandrasegaran; Ngoc-Bao Nguyen; Ngai-Man Cheung
Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM. (3%)Xikang Yang; Xuehai Tang; Songlin Hu; Jizhong Han
Demystifying Behavior-Based Malware Detection at Endpoints. (2%)Yigitcan Kaya; Yizheng Chen; Shoumik Saha; Fabio Pierazzi; Lorenzo Cavallaro; David Wagner; Tudor Dumitras
2024-05-08
Universal Adversarial Perturbations for Vision-Language Pre-trained Models. (99%)Peng-Fei Zhang; Zi Huang; Guangdong Bai
Adversarial Threats to Automatic Modulation Open Set Recognition in Wireless Networks. (99%)Yandie Yang; Sicheng Zhang; Kuixian Li; Qiao Tian; Yun Lin
Untargeted Adversarial Attack on Knowledge Graph Embeddings. (98%)Tianzhe Zhao; Jiaoyan Chen; Yanchi Ru; Qika Lin; Yuxia Geng; Jun Liu
Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations. (98%)Xuyang Zhong; Yixiao Huang; Chen Liu
Towards Accurate and Robust Architectures via Neural Architecture Search. (96%)Yuwei Ou; Yuqi Feng; Yanan Sun
Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution. (1%)Shuo Shao; Yiming Li; Hongwei Yao; Yiling He; Zhan Qin; Kui Ren
2024-05-07
Revisiting character-level adversarial attacks. (99%)Elias Abad Rocamora; Yongtao Wu; Fanghui Liu; Grigorios G. Chrysos; Volkan Cevher
Explainability-Informed Targeted Malware Misclassification. (99%)Quincy Card; Kshitiz Aryal; Maanak Gupta
Effective and Robust Adversarial Training against Data and Label Corruptions. (70%)Peng-Fei Zhang; Zi Huang; Xin-Shun Xu; Guangdong Bai
Going Proactive and Explanatory Against Malware Concept Drift. (1%)Yiling He; Junchi Lei; Zhan Qin; Kui Ren
Verified Neural Compressed Sensing. (1%)Rudy Bunel; Krishnamurthy Dvijotham; M. Pawan Kumar; Palma Alessandro De; Robert Stanforth
2024-05-06
Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability. (99%)Juanjuan Weng; Zhiming Luo; Shaozi Li
Cutting through buggy adversarial example defenses: fixing 1 line of code breaks Sabre. (99%)Nicholas Carlini
On Adversarial Examples for Text Classification by Perturbing Latent Representations. (99%)Korn Sooksatra; Bikram Khanal; Pablo Rivas
Is ReLU Adversarially Robust? (98%)Korn Sooksatra; Greg Hamerly; Pablo Rivas
Enhancing O-RAN Security: Evasion Attacks and Robust Defenses for Graph Reinforcement Learning-based Connection Management. (91%)Ravikumar Balakrishnan; Marius Arvinte; Nageen Himayat; Hosein Nikopour; Hassnaa Moustafa
BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection. (75%)Saket S. Chaturvedi; Lan Zhang; Wenbin Zhang; Pan He; Xiaoyong Yuan
Provably Unlearnable Data Examples. (64%)Derui Wang; Minhui Xue; Bo Li; Seyit Camtepe; Liming Zhu
DarkFed: A Data-Free Backdoor Attack in Federated Learning. (33%)Minghui Li; Wei Wan; Yuxuan Ning; Shengshan Hu; Lulu Xue; Leo Yu Zhang; Yichen Wang
UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images. (1%)Yiting Qu; Xinyue Shen; Yixin Wu; Michael Backes; Savvas Zannettou; Yang Zhang
Why is SAM Robust to Label Noise? (1%)Christina Baek; Zico Kolter; Aditi Raghunathan
Detecting Android Malware: From Neural Embeddings to Hands-On Validation with BERTroid. (1%)Meryam Chaieb; Mostafa Anouar Ghorab; Mohamed Aymen Saied
LaserEscape: Detecting and Mitigating Optical Probing Attacks. (1%)Saleh Khalaj Monfared; Kyle Mitard; Andrew Cannon; Domenic Forte; Shahin Tajik
2024-05-05
Defense against Joint Poison and Evasion Attacks: A Case Study of DERMS. (88%)Zain ul Abdeen; Padmaksha Roy; Ahmad Al-Tawaha; Rouxi Jia; Laura Freeman; Peter Beling; Chen-Ching Liu; Alberto Sangiovanni-Vincentelli; Ming Jin
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models. (15%)George-Octavian Barbulescu; Peter Triantafillou
Explainable Malware Detection with Tailored Logic Explained Networks. (2%)Peter Anthony; Francesco Giannini; Michelangelo Diligenti; Martin Homola; Marco Gori; Stefan Balogh; Jan Mojzis
2024-05-04
Leveraging the Human Ventral Visual Stream to Improve Neural Network Robustness. (92%)Zhenan Shao; Linjian Ma; Bo Li; Diane M. Beck
Updating Windows Malware Detectors: Balancing Robustness and Regression against Adversarial EXEmples. (83%)Matous Kozak; Luca Demetrio; Dmitrijs Trizna; Fabio Roli
Assessing Adversarial Robustness of Large Language Models: An Empirical Study. (76%)Zeyu Yang; Zhao Meng; Xiaochen Zheng; Roger Wattenhofer
2024-05-03
A Novel Approach to Guard from Adversarial Attacks using Stable Diffusion. (99%)Trinath Sai Subhash Reddy Pittala; Uma Maheswara Rao Meleti; Geethakrishna Puligundla
From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings. (99%)Firuz Juraev; Mohammed Abuhamad; Eric Chan-Tin; George K. Thiruvathukal; Tamer Abuhmed
ProFLingo: A Fingerprinting-based Copyright Protection Scheme for Large Language Models. (97%)Heng Jin; Chaoyu Zhang; Shanghao Shi; Wenjing Lou; Y. Thomas Hou
Impact of Architectural Modifications on Deep Learning Adversarial Robustness. (88%)Firuz Juraev; Mohammed Abuhamad; Simon S. Woo; George K Thiruvathukal; Tamer Abuhmed
Adaptive and robust watermark against model extraction attack. (38%)Kaiyi Pang; Tao Qi; Chuhan Wu; Minhao Bai
Robust Explainable Recommendation. (9%)Sairamvinay Vijayaraghavan; Prasant Mohapatra
Adversarial Botometer: Adversarial Analysis for Social Bot Detection. (1%)Shaghayegh Najari; Davood Rafiee; Mostafa Salehi; Reza Farahbakhsh
2024-05-02
Position Paper: Beyond Robustness Against Single Attack Types. (99%)Sihui Dai; Chong Xiang; Tong Wu; Prateek Mittal
Explainability Guided Adversarial Evasion Attacks on Malware Detectors. (98%)Kshitiz Aryal; Maanak Gupta; Mahmoud Abdelsalam; Moustafa Saleh
Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders. (88%)Yi Yu; Yufei Wang; Song Xia; Wenhan Yang; Shijian Lu; Yap-Peng Tan; Alex C. Kot
Poisoning Attacks on Federated Learning for Autonomous Driving. (75%)Sonakshi Garg; Hugo Jönsson; Gustav Kalander; Axel Nilsson; Bhhaanu Pirange; Viktor Valadi; Johan Östman
Adversarial Attacks on Reinforcement Learning Agents for Command and Control. (75%)Ahaan Dabholkar; James Z. Hare; Mark Mittrick; John Richardson; Nicholas Waytowich; Priya Narayanan; Saurabh Bagchi
Boosting Jailbreak Attack with Momentum. (41%)Yihao Zhang; Zeming Wei
Uniformly Stable Algorithms for Adversarial Training and Beyond. (10%)Jiancong Xiao; Jiawei Zhang; Zhi-Quan Luo; Asuman Ozdaglar
ATTAXONOMY: Unpacking Differential Privacy Guarantees Against Practical Adversaries. (2%)Rachel Cummings; Shlomi Hod; Jayshree Sarathy; Marika Swanberg
2024-05-01
Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing. (99%)Daniel Gibert; Luca Demetrio; Giulio Zizzo; Quan Le; Jordi Planes; Battista Biggio
JNI Global References Are Still Vulnerable: Attacks and Defenses. (12%)Yi He; Yuan Zhou; Yacong Gu; Purui Su; Qi Li; Yajin Zhou; Yong Jiang
Robustness of graph embedding methods for community detection. (2%)Zhi-Feng Wei; Pablo Moriano; Ramakrishnan Kannan
Exploiting Positional Bias for Query-Agnostic Generative Content in Search. (1%)Andrew Parry; Sean MacAvaney; Debasis Ganguly
2024-04-30
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective. (99%)Wanqi Zhou; Shuanghao Bai; Qibin Zhao; Badong Chen
Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective. (99%)Xiaoxuan Han; Songlin Yang; Wei Wang; Yang Li; Jing Dong
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples. (99%)Antonio Emanuele Cinà; Jérôme Rony; Maura Pintor; Luca Demetrio; Ambra Demontis; Battista Biggio; Ismail Ben Ayed; Fabio Roli
Provably Robust Conformal Prediction with Improved Efficiency. (98%)Ge Yan; Yaniv Romano; Tsui-Wei Weng
ASAM: Boosting Segment Anything Model with Adversarial Tuning. (98%)Bo Li; Haoke Xiao; Lv Tang
Adversarial Attacks and Defense for Conversation Entailment Task. (98%)Zhenning Yang; Ryan Krawec; Liang-Yuan Wu
Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment. (92%)Lei Wang; Desen Yuan
Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning. (81%)Xuanli He; Jun Wang; Qiongkai Xu; Pasquale Minervini; Pontus Stenetorp; Benjamin I. P. Rubinstein; Trevor Cohn
Let's Focus: Focused Backdoor Attack against Federated Transfer Learning. (75%)Marco Arazzi; Stefanos Koffas; Antonino Nocera; Stjepan Picek
VeriFence: Lightweight and Precise Spectre Defenses for Untrusted Linux Kernel Extensions. (1%)Luis Gerhorst; Henriette Herzog; Peter Wägemann; Maximilian Ott; Rüdiger Kapitza; Timo Hönig
Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World. (1%)Wen Yin; Jian Lou; Pan Zhou; Yulai Xie; Dan Feng; Yuhua Sun; Tailai Zhang; Lichao Sun
2024-04-29
Assessing Cybersecurity Vulnerabilities in Code Large Language Models. (99%)Md Imran Hossen; Jianyi Zhang; Yinzhi Cao; Xiali Hei
A Systematic Evaluation of Adversarial Attacks against Speech Emotion Recognition Models. (99%)Nicolas Facchinetti; Federico Simonetta; Stavros Ntalampiras
Certification of Speaker Recognition Models to Additive Perturbations. (54%)Dmitrii Korzh; Elvir Karimov; Mikhail Pautov; Oleg Y. Rogov; Ivan Oseledets
Espresso: Robust Concept Filtering in Text-to-Image Models. (15%)Anudeep Das; Vasisht Duddu; Rui Zhang; N. Asokan
Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots. (13%)Xi Xin; Giles Hooker; Fei Huang
Machine Learning for Windows Malware Detection and Classification: Methods, Challenges and Ongoing Research. (3%)Daniel Gibert
Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection. (1%)Konstantinos Tsigos; Evlampios Apostolidis; Spyridon Baxevanakis; Symeon Papadopoulos; Vasileios Mezaris
Harmonic Machine Learning Models are Robust. (1%)Nicholas S. Kersting; Yi Li; Aman Mohanty; Oyindamola Obisesan; Raphael Okochu
Enhancing IoT Security: A Novel Feature Engineering Approach for ML-Based Intrusion Detection Systems. (1%)Afsaneh Mahanipour; Hana Khamfroush
2024-04-28
Learnable Linguistic Watermarks for Tracing Model Extraction Attacks on Large Language Models. (1%)Minhao Bai; Kaiyi Pang; Yongfeng Huang
2024-04-27
Towards Robust Recommendation: A Review and an Adversarial Robustness Evaluation Library. (92%)Lei Cheng; Xiaowen Huang; Jitao Sang; Jian Yu
Privacy-Preserving Aggregation for Decentralized Learning with Byzantine-Robustness. (70%)Ali Reza Ghavamipour; Benjamin Zi Hao Zhao; Oguzhan Ersoy; Fatih Turkmen
Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks. (67%)Yassine Abbahaddou; Sofiane Ennadir; Johannes F. Lutzeyer; Michalis Vazirgiannis; Henrik Boström
Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics. (2%)Xiaoshuai Wu; Xin Liao; Bo Ou; Yuling Liu; Zheng Qin
2024-04-26
Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks. (99%)Yunzhen Feng; Tim G. J. Rudner; Nikolaos Tsilivis; Julia Kempe
Adversarial Examples: Generation Proposal in the Context of Facial Recognition Systems. (92%)Marina Fuster; Ignacio Vidaurreta
Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications. (54%)Quan Zhang; Binqi Zeng; Chijin Zhou; Gwihwan Go; Heyuan Shi; Yu Jiang
Evaluations of Machine Learning Privacy Defenses are Misleading. (3%)Michael Aerni; Jie Zhang; Florian Tramèr
Enhancing Privacy and Security of Autonomous UAV Navigation. (2%)Vatsal Aggarwal; Arjun Ramesh Kaushik; Charanjit Jutla; Nalini Ratha
Adversarial Reweighting with $\alpha$-Power Maximization for Domain Adaptation. (1%)Xiang Gu; Xi Yu; Yan Yang; Jian Sun; Zongben Xu
Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization. (1%)Dang Nguyen; Paymon Haddad; Eric Gan; Baharan Mirzasoleiman
Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifier. (1%)Natalie S. Frank
2024-04-25
Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach. (98%)Cristopher McIntyre-Garcia; Adrien Heymans; Beril Borali; Won-Sook Lee; Shiva Nejati
PAD: Patch-Agnostic Defense against Adversarial Patch Attacks. (92%)Lihua Jing; Rui Wang; Wenqi Ren; Xin Dong; Cong Zou
Defending Spiking Neural Networks against Adversarial Attacks through Image Purification. (84%)Weiran Chen; Qi Sun; Qi Xu
Don't Say No: Jailbreaking LLM by Suppressing Refusal. (67%)Yukai Zhou; Zhijie Huang; Feiyang Lu; Zhan Qin; Wenjie Wang
A Self-Organizing Clustering System for Unsupervised Distribution Shift Detection. (12%)Sebastián Basterrech; Line Clemmensen; Gerardo Rubino
Constructing Optimal Noise Channels for Enhanced Robustness in Quantum Machine Learning. (2%)David Winderl; Nicola Franco; Jeanette Miriam Lorenz
Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples. (2%)Kuofeng Gao; Jindong Gu; Yang Bai; Shu-Tao Xia; Philip Torr; Wei Liu; Zhifeng Li
Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs. (1%)Valeriia Cherepanova; James Zou
2024-04-24
Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks. (99%)Erh-Chung Chen; Pin-Yu Chen; I-Hsin Chung; Che-Rung Lee
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape. (99%)Sifat Muhammad Abdullah; Aravind Cheruvu; Shravya Kanchi; Taejoong Chung; Peng Gao; Murtuza Jadliwala; Bimal Viswanath
An Empirical Study of Aegis. (98%)Daniel Saragih; Paridhi Goel; Tejas Balaji; Alyssa Li
A General Black-box Adversarial Attack on Graph-based Fake News Detectors. (96%)Peican Zhu; Zechen Pan; Yang Liu; Jiwei Tian; Keke Tang; Zhen Wang
A Comparative Analysis of Adversarial Robustness for Quantum and Classical Machine Learning Models. (83%)Maximilian Wendlinger; Kilian Tscharke; Pascal Debus
MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception. (83%)Vidit Khazanchi; Pavan Kulkarni; Yuvaraj Govindarajulu; Manojkumar Parmar
Investigating the prompt leakage effect and black-box defenses for multi-turn LLM interactions. (45%)Divyansh Agarwal; Alexander R. Fabbri; Philippe Laban; Ben Risher; Shafiq Joty; Caiming Xiong; Chien-Sheng Wu
Universal Adversarial Triggers Are Not Universal. (16%)Nicholas Meade; Arkil Patel; Siva Reddy
CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning. (2%)Haolin Wu; Jing Chen; Ruiying Du; Cong Wu; Kun He; Xingcan Shang; Hao Ren; Guowen Xu
2024-04-23
Security Analysis of WiFi-based Sensing Systems: Threats from Perturbation Attacks. (61%)Hangcheng Cao; Wenbin Huang; Guowen Xu; Xianhao Chen; Ziyang He; Jingyang Hu; Hongbo Jiang; Yuguang Fang
Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures. (61%)Thanh Toan Nguyen; Quoc Viet Hung Nguyen; Thanh Tam Nguyen; Thanh Trung Huynh; Thanh Thi Nguyen; Matthias Weidlich; Hongzhi Yin
PoisonedFL: Model Poisoning Attacks to Federated Learning via Multi-Round Consistency. (54%)Yueqi Xie; Minghong Fang; Neil Zhenqiang Gong
Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models. (47%)Jingyao Xu; Yuetong Lu; Yandong Li; Siyang Lu; Dongdong Wang; Xiang Wei
Talk Too Much: Poisoning Large Language Models under Token Limit. (38%)Jiaming He; Wenbo Jiang; Guanyu Hou; Wenshu Fan; Rui Zhang; Hongwei Li
Leverage Variational Graph Representation For Model Poisoning on Federated Learning. (10%)Kai Li; Xin Yuan; Jingjing Zheng; Wei Ni; Falko Dressler; Abbas Jamalipour
Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structure. (2%)Tobias Ladner; Michael Eichelbeck; Matthias Althoff
Does It Make Sense to Explain a Black Box With Another Black Box? (1%)Julien Delaunay; Luis Galárraga; Christine Largouët
Graph Machine Learning in the Era of Large Language Models (LLMs). (1%)Wenqi Fan; Shijie Wang; Jiani Huang; Zhikai Chen; Yu Song; Wenzhuo Tang; Haitao Mao; Hui Liu; Xiaorui Liu; Dawei Yin; Qing Li
2024-04-22
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective. (98%)Yiming Liu; Kezhao Liu; Yao Xiao; Ziyi Dong; Xiaogang Xu; Pengxu Wei; Liang Lin
Double Privacy Guard: Robust Traceable Adversarial Watermarking against Face Recognition. (93%)Yunming Zhang; Dengpan Ye; Sipeng Shen; Caiyun Xie; Ziyi Liu; Jiacheng Deng; Long Tang
CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction. (74%)Wenhao Lan; Yijun Yang; Haihua Shen; Shan Li
Explicit Lipschitz Value Estimation Enhances Policy Robustness Against Perturbation. (67%)Xulin Chen; Ruipeng Liu; Garrett E. Katz
Audio Anti-Spoofing Detection: A Survey. (62%)Menglu Li; Yasaman Ahmadiadli; Xiao-Ping Zhang
Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning. (41%)Rong Wang; Guichen Zhou; Mingjun Gao; Yunpeng Xiao
Protecting Your LLMs with Information Bottleneck. (26%)Zichuan Liu; Zefan Wang; Linjie Xu; Jinyu Wang; Lei Song; Tianchun Wang; Chunlin Chen; Wei Cheng; Jiang Bian
Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs. (13%)Javier Rando; Francesco Croce; Kryštof Mitka; Stepan Shabalin; Maksym Andriushchenko; Nicolas Flammarion; Florian Tramèr
Deep Learning as Ricci Flow. (2%)Anthony Baptista; Alessandro Barp; Tapabrata Chakraborti; Chris Harbron; Ben D. MacArthur; Christopher R. S. Banerji
Hyp-OC: Hyperbolic One Class Classification for Face Anti-Spoofing. (1%)Kartik Narayan; Vishal M. Patel
Poisoning Attacks on Federated Learning-based Wireless Traffic Prediction. (1%)Zifan Zhang; Minghong Fang; Jiayuan Huang; Yuchen Liu
Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations. (1%)Sukmin Cho; Soyeong Jeong; Jeongyeon Seo; Taeho Hwang; Jong C. Park
2024-04-21
Attack on Scene Flow using Point Clouds. (98%)Haniyeh Ehsani Oskouie; Mohammad-Shahram Moin; Shohreh Kasaei
Fermi-Bose Machine. (96%)Mingshan Xie; Yuchen Wang; Haiping Huang
Robust EEG-based Emotion Recognition Using an Inception and Two-sided Perturbation Model. (50%)Shadi Sartipi; Mujdat Cetin
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs. (47%)Anselm Paulus; Arman Zharmagambetov; Chuan Guo; Brandon Amos; Yuandong Tian
Swap It Like Its Hot: Segmentation-based spoof attacks on eye-tracking images. (26%)Anish S. Narkar; Brendan David-John
Trojan Detection in Large Language Models: Insights from The Trojan Detection Challenge. (1%)Narek Maloyan; Ekansh Verma; Bulat Nutfullin; Bislan Ashinov
2024-04-20
Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion. (99%)Hongyu Zhu; Sichu Liang; Wentao Hu; Fangqi Li; Ju Jia; Shilin Wang
Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives. (99%)Chenxi Yang; Yujia Liu; Dingquan Li; Yan Zhong; Tingting Jiang
Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think. (99%)Haotian Xue; Yongxin Chen
Backdoor Attacks and Defenses on Semantic-Symbol Reconstruction in Semantic Communications. (41%)Yuan Zhou; Rose Qingyang Hu; Yi Qian
2024-04-19
How Real Is Real? A Human Evaluation Framework for Unrestricted Adversarial Examples. (99%)Dren Fazlija; Arkadij Orlov; Johanna Schrader; Monty-Maximilian Zühlke; Michael Rohs; Daniel Kudenko
AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation. (99%)Heqi Peng; Yunhong Wang; Ruijie Yang; Beichen Li; Rui Wang; Yuanfang Guo
A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only. (75%)Jiazhu Dai; Haoyu Sun
Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models. (5%)Zhenyang Ni; Rui Ye; Yuxi Wei; Zhen Xiang; Yanfeng Wang; Siheng Chen
MLSD-GAN -- Generating Strong High Quality Face Morphing Attacks using Latent Semantic Disentanglement. (3%)Aravinda Reddy PN; Raghavendra Ramachandra; Krothapalli Sreenivasa Rao; Pabitra Mitra
Model-Based Counterfactual Explanations Incorporating Feature Space Attributes for Tabular Data. (1%)Yuta Sumiya; Hayaru shouno
LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning. (1%)Beichen Li; Yuanfang Guo; Heqi Peng; Yangxi Li; Yunhong Wang
2024-04-18
Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors. (99%)Raz Lapid; Almog Dubin; Moshe Sipper
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing. (98%)Jiabao Ji; Bairu Hou; Zhen Zhang; Guanhua Zhang; Wenqi Fan; Qing Li; Yang Zhang; Gaowen Liu; Sijia Liu; Shiyu Chang
SA-Attack: Speed-adaptive stealthy adversarial attack on trajectory prediction. (98%)Huilin Yin; Jiaxiang Li; Pengju Zhen; Jun Yan
Enhance Robustness of Language Models Against Variation Attack through Graph Integration. (33%)Zi Xiong; Lizhi Qing; Yangyang Kang; Jiawei Liu; Hongsong Li; Changlong Sun; Xiaozhong Liu; Wei Lu
Uncovering Safety Risks of Large Language Models through Concept Activation Vector. (22%)Zhihao Xu; Ruixuan Huang; Changyu Chen; Shuai Wang; Xiting Wang
Proteus: Preserving Model Confidentiality during Graph Optimizations. (15%)Yubo Gao; Maryam Haghifam; Christina Giannoula; Renbo Tu; Gennady Pekhimenko; Nandita Vijaykumar
Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models. (2%)Shouwei Ruan; Yinpeng Dong; Hanqing Liu; Yao Huang; Hang Su; Xingxing Wei
Is There No Such Thing as a Bad Question? H4R: HalluciBot For Ratiocination, Rewriting, Ranking, and Routing. (1%)William Watson; Nicole Cho; Nishan Srishankar
2024-04-17
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data. (83%)Zixuan Zhu; Rui Wang; Cong Zou; Lihua Jing
GenFighter: A Generative and Evolutive Textual Attack Removal. (82%)Md Athikul Islam; Edoardo Serra; Sushil Jajodia
Utilizing Adversarial Examples for Bias Mitigation and Accuracy Enhancement. (80%)Pushkar Shukla; Dhruv Srikanth; Lee Cohen; Matthew Turk
Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers. (75%)Mohammad Javad Askarizadeh; Ebrahim Farahmand; Jorge Castro-Godinez; Ali Mahani; Laura Cabrera-Quiros; Carlos Salazar-Garcia
Exploring the Transferability of Visual Prompting for Multimodal Large Language Models. (2%)Yichi Zhang; Yinpeng Dong; Siyuan Zhang; Tianzan Min; Hang Su; Jun Zhu
Toward Understanding the Disagreement Problem in Neural Network Feature Attribution. (1%)Niklas Koenen; Marvin N. Wright
Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness. (1%)Hangtao Zhang; Shengshan Hu; Yichen Wang; Leo Yu Zhang; Ziqi Zhou; Xianlong Wang; Yanjun Zhang; Chao Chen
Towards Robust and Interpretable EMG-based Hand Gesture Recognition using Deep Metric Meta Learning. (1%)Simon Tam; Shriram Tallam Puranam Raghu; Étienne Buteau; Erik Scheme; Mounir Boukadoum; Alexandre Campeau-Lecours; Benoit Gosselin
2024-04-16
Efficiently Adversarial Examples Generation for Visual-Language Models under Targeted Transfer Scenarios using Diffusion Models. (99%)Qi Guo; Shanmin Pang; Xiaojun Jia; Qing Guo
Adversarial Identity Injection for Semantic Face Image Synthesis. (38%)Giuseppe Tarollo; Tomaso Fontanini; Claudio Ferrari; Guido Borghi; Andrea Prati
Robust Noisy Label Learning via Two-Stream Sample Distillation. (1%)Sihan Bai; Sanping Zhou; Zheng Qin; Le Wang; Nanning Zheng
2024-04-15
Black-box Adversarial Transferability: An Empirical Study in Cybersecurity Perspective. (99%)Khushnaseeb Roshan; Aasim Zafar
Towards a Novel Perspective on Adversarial Examples Driven by Frequency. (99%)Zhun Zhang; Yi Zeng; Qihe Liu; Shijie Zhou
Ti-Patch: Tiled Physical Adversarial Patch for no-reference video quality metrics. (83%)Victoria Leonenkova; Ekaterina Shumitskaya; Anastasia Antsiferova; Dmitriy Vatolin
Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label. (1%)Byeongkeun Kang; Sinhae Cha; Yeejin Lee
Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data Augmentation. (1%)Shangqing Liu; Wei Ma; Jian Wang; Xiaofei Xie; Ruitao Feng; Yang Liu
Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering. (1%)Zaid Khan; Yun Fu
2024-04-14
Counteracting Concept Drift by Learning with Future Malware Predictions. (96%)Branislav Bosansky; Lada Hospodkova; Michal Najman; Maria Rigaki; Elnaz Babayeva; Viliam Lisy
Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models. (96%)Peifei Zhu; Tsubasa Takahashi; Hirokatsu Kataoka
Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies. (76%)Brian R. Bartoldson; James Diffenderfer; Konstantinos Parasyris; Bhavya Kailkhura
FaceCat: Enhancing Face Recognition Security with a Unified Generative Model Framework. (22%)Jiawei Chen; Xiao Yang; Yinpeng Dong; Hang Su; Jianteng Peng; Zhaoxia Yin
2024-04-13
Stability and Generalization in Free Adversarial Training. (96%)Xiwei Cheng; Kexin Fu; Farzan Farnia
Proof-of-Learning with Incentive Security. (2%)Zishuo Zhao; Zhixuan Fang; Xuechao Wang; Xi Chen; Yuan Zhou
2024-04-12
PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis. (99%)Dipkamal Bhusal; Md Tanvirul Alam; Monish K. Veerabhadran; Michael Clifford; Sara Rampazzi; Nidhi Rastogi
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts. (99%)Yang Li; Songlin Yang; Wei Wang; Ziwen He; Bo Peng; Jing Dong
Struggle with Adversarial Defense? Try Diffusion. (99%)Yujie Li; Yanbin Wang; Haitao Xu; Bin Liu; Jianguo Sun; Zhenhao Guo; Wenrui Ma
Multimodal Attack Detection for Action Recognition Models. (83%)Furkan Mumcu; Yasin Yilmaz
A Survey of Neural Network Robustness Assessment in Image Recognition. (83%)Jie Wang; Jun Ai; Minyan Lu; Haoran Su; Dan Yu; Yutao Zhang; Junda Zhu; Jingyu Liu
Practical Region-level Attack against Segment Anything Models. (81%)Yifan Shen; Zhengyuan Li; Gang Wang
FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models. (69%)Yanting Wang; Wei Zou; Jinyuan Jia
Mitigating Cascading Effects in Large Adversarial Graph Environments. (2%)James D. Cunningham; Conrad S. Tucker
On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation. (1%)Agneet Chatterjee; Tejas Gokhale; Chitta Baral; Yezhou Yang
Empowering Malware Detection Efficiency within Processing-in-Memory Architecture. (1%)Sreenitha Kasarapu; Sathwika Bavikadi; Sai Manoj Pudukotai Dinakarrao
2024-04-11
Persistent Classification: A New Approach to Stability of Data and Adversarial Examples. (98%)Brian Bell; Michael Geyer; David Glickenstein; Keaton Hamm; Carlos Scheidegger; Amanda Fernandez; Juston Moore
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization. (98%)Runqi Lin; Chaojian Yu; Tongliang Liu
Backdoor Contrastive Learning via Bi-level Trigger Optimization. (96%)Weiyu Sun; Xinyu Zhang; Hao Lu; Yingcong Chen; Ting Wang; Jinghui Chen; Lu Lin
Adversarial Robustness of Distilled and Pruned Deep Learning-based Wireless Classifiers. (92%)Nayan Moni Baishya; B. R. Manoj
CodeFort: Robust Training for Code Generation Models. (33%)Yuhao Zhang; Shiqi Wang; Haifeng Qian; Zijian Wang; Mingyue Shang; Linbo Liu; Sanjay Krishna Gouda; Baishakhi Ray; Murali Krishna Ramanathan; Xiaofei Ma; Anoop Deoras
AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs. (12%)Zeyi Liao; Huan Sun
LeapFrog: The Rowhammer Instruction Skip Attack. (8%)Andrew Adiletta; M. Caner Tol; Kemal Derya; Berk Sunar; Saad Islam
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies. (1%)Zichao Li; Cihang Xie; Ekin Dogus Cubuk
2024-04-10
Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data. (99%)Yu Qiao; Chaoning Zhang; Apurba Adhikary; Choong Seon Hong
Lost in Translation: Modern Neural Networks Still Struggle With Small Realistic Image Transformations. (82%)Ofir Shifman; Yair Weiss
Adversarial purification for no-reference image-quality metrics: applicability study and new methods. (26%)Aleksandr Gushchin; Anna Chistyakova; Vladislav Minashkin; Anastasia Antsiferova; Dmitriy Vatolin
Simpler becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora? (2%)Miriam Anschütz; Edoardo Mosca; Georg Groh
TrajPRed: Trajectory Prediction with Region-based Relation Learning. (1%)Chen Zhou; Ghassan AlRegib; Armin Parchami; Kunjan Singh
2024-04-09
Towards Building a Robust Toxicity Predictor. (99%)Dmitriy Bespalov; Sourav Bhabesh; Yi Xiang; Liutong Zhou; Yanjun Qi
On adversarial training and the 1 Nearest Neighbor classifier. (99%)Amir Hagai; Yair Weiss
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks. (80%)Jianlang Chen; Xuhong Ren; Qing Guo; Felix Juefei-Xu; Di Lin; Wei Feng; Lei Ma; Jianjun Zhao
Towards Robust Domain Generation Algorithm Classification. (80%)Arthur Drichel; Marc Meyer; Ulrike Meyer
SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models. (41%)Xinfeng Li; Yuchen Yang; Jiangyi Deng; Chen Yan; Yanjiao Chen; Xiaoyu Ji; Wenyuan Xu
Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs. (31%)Bibek Upadhayay; Vahid Behzadan
Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning. (26%)Emre Ozfatura; Kerem Ozfatura; Alptekin Kupcu; Deniz Gunduz
How to Craft Backdoors with Unlabeled Data Alone? (1%)Yifei Wang; Wenhan Ma; Yisen Wang
2024-04-08
Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing. (99%)Chengyan Fu; Wenjie Wang
David and Goliath: An Empirical Evaluation of Attacks and Defenses for QNNs at the Deep Edge. (99%)Miguel Costa; Sandro Pinto
BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack. (99%)Viet Quoc Vo; Ehsan Abbasnejad; Damith C. Ranasinghe
Case Study: Neural Network Malware Detection Verification for Feature and Image Datasets. (98%)Preston K. Robinette; Diego Manzanas Lopez; Serena Serbinowska; Kevin Leach; Taylor T. Johnson
Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey. (98%)Naveen Karunanayake; Ravin Gunawardena; Suranga Seneviratne; Sanjay Chawla
Quantum Adversarial Learning for Kernel Methods. (75%)Giuseppe Montalbano; Leonardo Banchi
Investigating the Impact of Quantization on Adversarial Robustness. (50%)Qun Li; Yuan Meng; Chen Tang; Jiacheng Jiang; Zhi Wang
SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation. (1%)Heyuan Li; Ce Chen; Tianhao Shi; Yuda Qiu; Sizhe An; Guanying Chen; Xiaoguang Han
2024-04-07
Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods. (99%)Roopkatha Dey; Aivy Debnath; Sayak Kumar Dutta; Kaustav Ghosh; Arijit Mitra; Arghya Roy Chowdhury; Jaydip Sen
Enabling Privacy-Preserving Cyber Threat Detection with Federated Learning. (15%)Yu Bi; Yekai Li; Xuan Feng; Xianghang Mi
How much reliable is ChatGPT's prediction on Information Extraction under Input Perturbations? (5%)Ishani Mondal; Abhilasha Sancheti
SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. (1%)Mael Jullien; Marco Valentino; André Freitas
2024-04-06
CANEDERLI: On The Impact of Adversarial Training and Transferability on CAN Intrusion Detection Systems. (86%)Francesco Marchiori; Mauro Conti
Learning Minimal NAP Specifications for Neural Network Verification. (80%)Chuqin Geng; Zhaoyue Wang; Haolin Ye; Saifei Liao; Xujie Si
Data Poisoning Attacks on Off-Policy Policy Evaluation Methods. (67%)Elita Lobo; Harvineet Singh; Marek Petrik; Cynthia Rudin; Himabindu Lakkaraju
Goal-guided Generative Prompt Injection Attack on Large Language Models. (67%)Chong Zhang; Mingyu Jin; Qinkai Yu; Chengzhi Liu; Haochen Xue; Xiaobo Jin
Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training. (61%)Shizhan Gong; Qi Dou; Farzan Farnia
Exploiting Sequence Number Leakage: TCP Hijacking in NAT-Enabled Wi-Fi Networks. (3%)Yuxiang Yang; Xuewei Feng; Qi Li; Kun Sun; Ziqiang Wang; Ke Xu
2024-04-05
Evaluating Adversarial Robustness: A Comparison Of FGSM, Carlini-Wagner Attacks, And The Role of Distillation as Defense Mechanism. (99%)Trilokesh Ranjan Sarkar; Nilanjan Das; Pralay Sankar Maitra; Bijoy Some; Ritwik Saha; Orijita Adhikary; Bishal Bose; Jaydip Sen
Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection. (98%)João Vitorino; Miguel Silva; Eva Maia; Isabel Praça
DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models. (15%)Khawar Islam; Muhammad Zaigham Zaheer; Arif Mahmood; Karthik Nandakumar
Compositional Estimation of Lipschitz Constants for Deep Neural Networks. (13%)Yuezhu Xu; S. Sivaranjani
Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning. (12%)K Naveen Kumar; C Krishna Mohan; Aravind Machiry
2024-04-04
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks. (99%)Lei Zhang; Yuhang Zhou; Yi Yang; Xinbo Gao
FACTUAL: A Novel Framework for Contrastive Learning Based Robust SAR Image Classification. (98%)Xu Wang; Tian Ye; Rajgopal Kannan; Viktor Prasanna
Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning. (16%)Hongsheng Hu; Shuo Wang; Tian Dong; Minhui Xue
Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual Explanations. (8%)Fatima Ezzeddine; Omran Ayoub; Silvia Giordano
Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks? (2%)Shuo Chen; Zhen Han; Bailan He; Zifeng Ding; Wenqian Yu; Philip Torr; Volker Tresp; Jindong Gu
2024-04-03
Adversarial Attacks and Dimensionality in Text Classifiers. (99%)Nandish Chattopadhyay; Atreya Goswami; Anupam Chattopadhyay
Unsegment Anything by Simulating Deformation. (97%)Jiahao Lu; Xingyi Yang; Xinchao Wang
"Are Adversarial Phishing Webpages a Threat in Reality?" Understanding the Users' Perception of Adversarial Webpages. (81%)Ying Yuan; Qingying Hao; Giovanni Apruzzese; Mauro Conti; Gang Wang
JailBreakV-28K: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks. (75%)Weidi Luo; Siyuan Ma; Xiaogeng Liu; Xiaoyu Guo; Chaowei Xiao
Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game. (11%)Qianqiao Xu; Zhiliang Tian; Hongyan Wu; Zhen Huang; Yiping Song; Feng Liu; Dongsheng Li
A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability. (9%)Jie Zhu; Jirong Zha; Ding Li; Leye Wang
Steganographic Passport: An Owner and User Verifiable Credential for Deep Model IP Protection Without Retraining. (1%)Qi Cui; Ruohan Meng; Chaohui Xu; Chip-Hong Chang
2024-04-02
Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack. (99%)Ying Zhou; Ben He; Le Sun
ADVREPAIR:Provable Repair of Adversarial Attack. (99%)Zhiming Chi; Jianan Ma; Pengfei Yang; Cheng-Chao Huang; Renjue Li; Xiaowei Huang; Lijun Zhang
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models. (97%)Jiachen Ma; Anda Cao; Zhiqing Xiao; Yijiang Li; Jie Zhang; Chao Ye; Junbo Zhao
One Noise to Rule Them All: Multi-View Adversarial Attacks with Universal Perturbation. (92%)Mehmet Ergezer; Phat Duong; Christian Green; Tommy Nguyen; Abdurrahman Zeybey
Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay. (88%)Yuhang Zhou; Zhongyun Hua
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks. (83%)Maksym Andriushchenko; Francesco Croce; Nicolas Flammarion
READ: Improving Relation Extraction from an ADversarial Perspective. (81%)Dawei Li; William Hogan; Jingbo Shang
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors. (64%)Victoria Graf; Qin Liu; Muhao Chen
Red-Teaming Segment Anything Model. (45%)Krzysztof Jankowski; Bartlomiej Sobieski; Mateusz Kwiatkowski; Jakub Szulc; Michal Janik; Hubert Baniecki; Przemyslaw Biecek
Towards Robust 3D Pose Transfer with Adversarial Learning. (31%)Haoyu Chen; Hao Tang; Ehsan Adeli; Guoying Zhao
Designing a Photonic Physically Unclonable Function Having Resilience to Machine Learning Attacks. (12%)Elena R. Henderson; Jessie M. Henderson; Hiva Shahoei; William V. Oxford; Eric C. Larson; Duncan L. MacFarlane; Mitchell A. Thornton
Exploring Backdoor Vulnerabilities of Chat Models. (2%)Yunzhuo Hao; Wenkai Yang; Yankai Lin
CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation. (1%)Townim Faisal Chowdhury; Kewen Liao; Vu Minh Hieu Phan; Minh-Son To; Yutong Xie; Kevin Hung; David Ross; Anton van den Hengel; Johan W. Verjans; Zhibin Liao
2024-04-01
The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness. (99%)Xuran Li; Peng Wu; Yanting Chen; Xingjun Ma; Zhen Zhang; Kaixiang Dong
Multi-granular Adversarial Attacks against Black-box Neural Ranking Models. (99%)Yu-An Liu; Ruqing Zhang; Jiafeng Guo; Rijke Maarten de; Yixing Fan; Xueqi Cheng
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks. (93%)Zhiyuan Cheng; Zhaoyi Liu; Tengda Guo; Shiwei Feng; Dongfang Liu; Mingjie Tang; Xiangyu Zhang
Poisoning Decentralized Collaborative Recommender System and Its Countermeasures. (33%)Ruiqi Zheng; Liang Qu; Tong Chen; Kai Zheng; Yuhui Shi; Hongzhi Yin
Can Biases in ImageNet Models Explain Generalization? (10%)Paul Gavrikov; Janis Keuper
UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models. (10%)Zihan Guan; Mengxuan Hu; Sheng Li; Anil Vullikanti
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models. (2%)Yuxin Wen; Leo Marchyok; Sanghyun Hong; Jonas Geiping; Tom Goldstein; Nicholas Carlini
An incremental hybrid adaptive network-based IDS in Software Defined Networks to detect stealth attacks. (1%)Abdullah H Alqahtani
2024-03-31
PID Control-Based Self-Healing to Improve the Robustness of Large Language Models. (75%)Zhuotong Chen; Zihu Wang; Yifan Yang; Qianxiao Li; Zheng Zhang
Machine Learning Robustness: A Primer. (62%)Houssem Ben Braiek; Foutse Khomh
2024-03-30
STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario. (99%)Renyang Liu; Kwok-Yan Lam; Wei Zhou; Sixing Wu; Jun Zhao; Dongting Hu; Mingming Gong
Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches. (98%)Lingxuan Wu; Xiao Yang; Yinpeng Dong; Liuwei Xie; Hang Su; Jun Zhu
Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning. (5%)Xiaopeng Xie; Ming Yan; Xiwen Zhou; Chenlong Zhao; Suli Wang; Yong Zhang; Joey Tianyi Zhou
2024-03-29
On Inherent Adversarial Robustness of Active Vision Systems. (99%)Amitangshu Mukherjee; Timur Ibrayev; Kaushik Roy
Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions. (68%)Runhao Zeng; Xiaoyong Chen; Jiaming Liang; Huisi Wu; Guangzhong Cao; Yong Guo
Deepfake Sentry: Harnessing Ensemble Intelligence for Resilient Detection and Generalisation. (8%)Liviu-Daniel University "Politehnica" of Bucharest, Romania Ştefan; Dan-Cristian University "Politehnica" of Bucharest, Romania Stanciu; Mihai University "Politehnica" of Bucharest, Romania Dogariu; Mihai Gabriel University "Politehnica" of Bucharest, Romania Constantin; Andrei Cosmin University "Politehnica" of Bucharest, Romania Jitaru; Bogdan University "Politehnica" of Bucharest, Romania Ionescu
The Impact of Prompts on Zero-Shot Detection of AI-Generated Text. (2%)Kaito Taguchi; Yujie Gu; Kouichi Sakurai
GDA: Generalized Diffusion for Robust Test-time Adaptation. (1%)Yun-Yun Tsai; Fu-Chen Chen; Albert Y. C. Chen; Junfeng Yang; Che-Chun Su; Min Sun; Cheng-Hao Kuo
Efficient Data-Free Model Stealing with Label Diversity. (1%)Yiyong Liu; Rui Wen; Michael Backes; Yang Zhang
Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets. (1%)Shadi Manafi; Nikhil Krishnaswamy
2024-03-28
Towards Understanding Dual BN In Hybrid Adversarial Training. (82%)Chenshuang Zhang; Chaoning Zhang; Kang Zhang; Axi Niu; Junmo Kim; In So Kweon
Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset. (82%)Janis Goldzycher; Paul Röttger; Gerold Schneider
On the Robustness of LDP Protocols for Numerical Attributes under Data Poisoning Attacks. (41%)Xiaoguang Li; Zitao Li; Ninghui Li; Wenhai Sun
MedBN: Robust Test-Time Adaptation against Malicious Test Samples. (10%)Hyejin Park; Jeongyeon Hwang; Sunung Mun; Sangdon Park; Jungseul Ok
Imperceptible Protection against Style Imitation from Diffusion Models. (2%)Namhyuk Ahn; Wonhyuk Ahn; KiYoon Yoo; Daesik Kim; Seung-Hun Nam
A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks. (1%)Orson Mengara
2024-03-27
Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networks. (99%)Tian Ye; Rajgopal Kannan; Viktor Prasanna; Carl Busart
CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection. (99%)Jiayi Zhu; Qing Guo; Felix Juefei-Xu; Yihao Huang; Yang Liu; Geguang Pu
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models. (98%)Yanting Wang; Hongye Fu; Wei Zou; Jinyuan Jia
Bayesian Learned Models Can Detect Adversarial Malware For Free. (97%)Bao Gia Doan; Dang Quang Nguyen; Paul Montague; Tamas Abraham; Vel Olivier De; Seyit Camtepe; Salil S. Kanhere; Ehsan Abbasnejad; Damith C. Ranasinghe
MisGUIDE : Defense Against Data-Free Deep Learning Model Extraction. (95%)Mahendra Gurve; Sankar Behera; Satyadev Ahlawat; Yamuna Prasad
Towards Sustainable SecureML: Quantifying Carbon Footprint of Adversarial Machine Learning. (83%)Syed Mhamudul Hasan; Abdur R. Shahid; Ahmed Imteaj
Deep Learning for Robust and Explainable Models in Computer Vision. (82%)Mohammadreza Amirian
SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks. (81%)Brian Formento; Wenjie Feng; Chuan Sheng Foo; Luu Anh Tuan; See-Kiong Ng
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models. (54%)Patrick Chao; Edoardo Debenedetti; Alexander Robey; Maksym Andriushchenko; Francesco Croce; Vikash Sehwag; Edgar Dobriban; Nicolas Flammarion; George J. Pappas; Florian Tramer; Hamed Hassani; Eric Wong
Vulnerability Detection with Code Language Models: How Far Are We? (26%)Yangruibo Ding; Yanjun Fu; Omniyyah Ibrahim; Chawin Sitawarin; Xinyun Chen; Basel Alomair; David Wagner; Baishakhi Ray; Yizheng Chen
Spikewhisper: Temporal Spike Backdoor Attacks on Federated Neuromorphic Learning over Low-power Devices. (15%)Hanqing Fu; Gaolei Li; Jun Wu; Jianhua Li; Xi Lin; Kai Zhou; Yuchen Liu
Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning. (15%)Soumyendu Sarkar; Ashwin Ramesh Babu; Sajad Mousavi; Vineet Gundecha; Avisek Naug; Sahand Ghorbanpour
The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision. (11%)Andreas Müller; Erwin Quiring
Fact Checking Beyond Training Set. (1%)Payam Karisani; Heng Ji
BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection. (1%)Changshun Wu; Weicheng He; Chih-Hong Cheng; Xiaowei Huang; Saddek Bensalem
2024-03-26
DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protection. (92%)Sihan Shang; Jiancheng Yang; Zhenglong Sun; Pascal Fua
FaultGuard: A Generative Approach to Resilient Fault Prediction in Smart Electrical Grids. (78%)Emad Efatinasab; Francesco Marchiori; Alessandro Brighente; Mirco Rampazzo; Mauro Conti
Boosting Adversarial Training via Fisher-Rao Norm-based Regularization. (69%)Xiangyu Yin; Wenjie Ruan
Optimization-based Prompt Injection Attack to LLM-as-a-Judge. (45%)Jiawen Shi; Zenghui Yuan; Yinuo Liu; Yue Huang; Pan Zhou; Lichao Sun; Neil Zhenqiang Gong
Targeted Visualization of the Backbone of Encoder LLMs. (9%)Isaac Roberts; Alexander Schulz; Luca Hermes; Barbara Hammer
Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning. (1%)Joshua C. Zhao; Ahaan Dabholkar; Atul Sharma; Saurabh Bagchi
Exploring LLMs as a Source of Targeted Synthetic Textual Data to Minimize High Confidence Misclassifications. (1%)Philip Lippmann; Matthijs Spaan; Jie Yang
2024-03-25
$\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models. (99%)Yue Xu; Wenjie Wang
Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving. (98%)Junhao Zheng; Chenhao Lin; Jiahao Sun; Zhengyu Zhao; Qian Li; Chao Shen
The Anatomy of Adversarial Attacks: Concept-based XAI Dissection. (87%)Georgii Mikriukov; Gesina Schwalbe; Franz Motzkus; Korinna Bade
DeepKnowledge: Generalisation-Driven Deep Learning Testing. (82%)Sondess Missaoui; Simos Gerasimou; Nikolaos Matragkas
Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors. (70%)Md Abdul Kadir; GowthamKrishna Addluri; Daniel Sonntag
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning. (69%)Siyuan Cheng; Guanhong Tao; Yingqi Liu; Guangyu Shen; Shengwei An; Shiwei Feng; Xiangzhe Xu; Kaiyuan Zhang; Shiqing Ma; Xiangyu Zhang
Model-less Is the Best Model: Generating Pure Code Implementations to Replace On-Device DL Models. (1%)Mingyi Zhou; Xiang Gao; Pei Liu; John Grundy; Chunyang Chen; Xiao Chen; Li Li
2024-03-24
Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals. (99%)Rui Zheng; Yuhao Zhou; Zhiheng Xi; Tao Gui; Qi Zhang; Xuanjing Huang
Ensemble Adversarial Defense via Integration of Multiple Dispersed Low Curvature Models. (98%)Kaikang Zhao; Xi Chen; Wei Huang; Liuxin Ding; Xianglong Kong; Fan Zhang
Robust Diffusion Models for Adversarial Purification. (83%)Guang Lin; Zerui Tao; Jianhai Zhang; Toshihisa Tanaka; Qibin Zhao
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning. (5%)Siyuan Liang; Kuanrong Liu; Jiajun Gong; Jiawei Liang; Yuan Xun; Ee-Chien Chang; Xiaochun Cao
Rumor Detection with a novel graph neural network approach. (4%)Tianrui Liu; Qi Cai; Changxin Xu; Bo Hong; Fanghao Ni; Yuxin Qiao; Tsungwei Yang
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion. (2%)Hossein Souri; Arpit Bansal; Hamid Kazemi; Liam Fowl; Aniruddha Saha; Jonas Geiping; Andrew Gordon Wilson; Rama Chellappa; Tom Goldstein; Micah Goldblum
A General and Efficient Federated Split Learning with Pre-trained Image Transformers for Heterogeneous Data. (1%)Yifan Shi; Yuhui Zhang; Ziyue Huang; Xiaofeng Yang; Li Shen; Wei Chen; Xueqian Wang
2024-03-23
Towards Adversarial Robustness And Backdoor Mitigation in SSL. (76%)Aryan Satpathy; Nilaksh Singh; Dhruva Rajwade; Somesh Kumar
Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions. (64%)Kaiwen Wang; Yinzhe Shen; Martin Lauer
2024-03-22
Robust optimization for adversarial learning with finite sample complexity guarantees. (96%)André Bertolace; Konstatinos Gatsis; Kostas Margellos
A Transfer Attack to Image Watermarks. (95%)Yuepeng Hu; Zhengyuan Jiang; Moyang Guo; Neil Gong
From Hardware Fingerprint to Access Token: Enhancing the Authentication on IoT Devices. (26%)Yue Xiao; Yi He; Xiaoli Zhang; Qian Wang; Renjie Xie; Kun Sun; Ke Xu; Qi Li
Clean-image Backdoor Attacks. (12%)Dazhong Rong; Guoyao Yu; Shuheng Shen; Xinyi Fu; Peng Qian; Jianhai Chen; Qinming He; Xing Fu; Weiqiang Wang
Forward Learning for Gradient-based Black-box Saliency Map Generation. (1%)Zeliang Zhang; Mingqian Feng; Jinyang Jiang; Rongyi Zhu; Yijie Peng; Chenliang Xu
2024-03-21
Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking. (99%)Qianyu Guo; Jiaming Fu; Yawen Lu; Dongming Gan
Few-Shot Adversarial Prompt Learning on Vision-Language Models. (98%)Yiwei Zhou; Xiaobo Xia; Zhiwei Lin; Bo Han; Tongliang Liu
Reversible Jump Attack to Textual Classifiers with Modification Reduction. (98%)Mingze Ni; Zhensu Sun; Wei Liu
Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures. (82%)Sayanton V. Dibbo; Adam Breuer; Juston Moore; Michael Teti
Adversary-Robust Graph-Based Learning of WSIs. (45%)Saba Heidari Gheshlaghi; Milan Aryal; Nasim Yahyasoltani; Masoud Ganji
Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations. (4%)Xun Lin; Yi Yu; Song Xia; Jue Jiang; Haoran Wang; Zitong Yu; Yizhong Liu; Ying Fu; Shuai Wang; Wenzhong Tang; Alex Kot
2024-03-20
FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs. (97%)Jinmin Li; Kuofeng Gao; Yang Bai; Jingyun Zhang; Shu-tao Xia; Yisen Wang
DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation. (96%)Yifan Wu; Jiawei Du; Ping Liu; Yuewei Lin; Wenqing Cheng; Wei Xu
Capsule Neural Networks as Noise Stabilizer for Time Series Data. (93%)Soyeon Kim; Jihyeon Seong; Hyunkyung Han; Jaesik Choi
Adversarial Attacks and Defenses in Automated Control Systems: A Comprehensive Benchmark. (70%)Vitaliy Pozdnyakov; Aleksandr Kovalenko; Ilya Makarov; Mikhail Drobyshevskiy; Kirill Lukyanov
Certified Human Trajectory Prediction. (61%)Mohammadhossein Bahari; Saeed Saadatnejad; Amirhossein Asgari Farsangi; Seyed-Mohsen Moosavi-Dezfooli; Alexandre Alahi
Have You Poisoned My Data? Defending Neural Networks against Data Poisoning. (54%)Gaspari Fabio De; Dorjan Hitaj; Luigi V. Mancini
Mask-based Invisible Backdoor Attacks on Object Detection. (50%)Shin Jeong Jin
Defending Against Indirect Prompt Injection Attacks With Spotlighting. (31%)Keegan Hines; Gary Lopez; Matthew Hall; Federico Zarfati; Yonatan Zunger; Emre Kiciman
Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks. (11%)Seunguk Yu; Juhwan Choi; Youngbin Kim
BadEdit: Backdooring large language models by model editing. (1%)Yanzhou Li; Tianlin Li; Kangjie Chen; Jian Zhang; Shangqing Liu; Wenhan Wang; Tianwei Zhang; Yang Liu
Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models. (1%)Adian Liusie; Yassir Fathullah; Mark J. F. Gales
Threats, Attacks, and Defenses in Machine Unlearning: A Survey. (1%)Ziyao Liu; Huanyi Ye; Chen Chen; Kwok-Yan Lam
2024-03-19
As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks? (99%)Anjun Hu; Jindong Gu; Francesco Pinto; Konstantinos Kamnitsas; Philip Torr
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory. (99%)Sensen Gao; Xiaojun Jia; Xuhong Ren; Ivor Tsang; Qing Guo
ADAPT to Robustify Prompt Tuning Vision Transformers. (98%)Masih Eskandar; Tooba Imtiaz; Zifeng Wang; Jennifer Dy
Marlin: Knowledge-Driven Analysis of Provenance Graphs for Efficient and Robust Detection of Cyber Attacks. (75%)Zhenyuan Li; Yangyang Wei; Xiangmin Shen; Lingzhi Wang; Yan Chen; Haitao Xu; Shouling Ji; Fan Zhang; Liang Hou; Wenmao Liu; Xuhong Zhang; Jianwei Ying
Resilience in Online Federated Learning: Mitigating Model-Poisoning Attacks via Partial Sharing. (9%)Ehsan Lari; Reza Arablouei; Vinay Chakravarthi Gogineni; Stefan Werner
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content. (8%)Zhuowen Yuan; Zidi Xiong; Yi Zeng; Ning Yu; Ruoxi Jia; Dawn Song; Bo Li
Robust NAS under adversarial training: benchmark, theory, and beyond. (2%)Yongtao Wu; Fanghui Liu; Carl-Johann Simon-Gabriel; Grigorios G Chrysos; Volkan Cevher
Discover and Mitigate Multiple Biased Subgroups in Image Classifiers. (1%)Zeliang Zhang; Mingqian Feng; Zhiheng Li; Chenliang Xu
2024-03-18
Diffusion Denoising as a Certified Defense against Clean-label Poisoning. (99%)Sanghyun Hong; Nicholas Carlini; Alexey Kurakin
SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator. (99%)Javad Rafiei Asl; Mohammad H. Rafiei; Manar Alohaly; Daniel Takabi
LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model. (99%)Yuxin Cao; Jinghao Li; Xi Xiao; Derui Wang; Minhui Xue; Hao Ge; Wei Liu; Guangwu Hu
Invisible Backdoor Attack Through Singular Value Decomposition. (96%)Wenmin Chen; Xiaowei Xu
Problem space structural adversarial attacks for Network Intrusion Detection Systems based on Graph Neural Networks. (88%)Andrea Venturi; Dario Stabili; Mirco Marchetti
Impart: An Imperceptible and Effective Label-Specific Backdoor Attack. (83%)Jingke Zhao; Zan Wang; Yongwei Wang; Lanjun Wang
SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications. (78%)Amira Guesmi; Muhammad Abdullah Hanif; Ihsen Alouani; Bassem Ouni; Muhammad Shafique
Electioneering the Network: Dynamic Multi-Step Adversarial Attacks for Community Canvassing. (61%)Saurabh Sharma; Ambuj SIngh
Advancing Time Series Classification with Multimodal Language Modeling. (1%)Mingyue Cheng; Yiheng Chen; Qi Liu; Zhiding Liu; Yucong Luo
2024-03-17
Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization. (99%)Yujia Liu; Chenxi Yang; Dingquan Li; Jianhao Ding; Tingting Jiang
A Modified Word Saliency-Based Adversarial Attack on Text Classification Models. (99%)Hetvi Waghela; Sneha Rakshit; Jaydip Sen
Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM. (99%)Linyu Tang; Lei Zhang
Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentation. (76%)Silvia Corbara; Alejandro Moreo
RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning. (50%)Javad Rafiei Asl; Prajwal Panzade; Eduardo Blanco; Daniel Takabi; Zhipeng Cai
COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits. (22%)Mintong Kang; Nezihe Merve Gürel; Linyi Li; Bo Li
A Dual-Tier Adaptive One-Class Classification IDS for Emerging Cyberthreats. (9%)Md. Ashraf Uddin; Sunil Aryal; Mohamed Reda Bouadjenek; Muna Al-Hawawreh; Md. Alamin Talukder
Hierarchical Classification for Intrusion Detection System: Effective Design and Empirical Analysis. (2%)Md. Ashraf Uddin; Sunil Aryal; Mohamed Reda Bouadjenek; Muna Al-Hawawreh; Md. Alamin Talukder
CBR - Boosting Adaptive Classification By Retrieval of Encrypted Network Traffic with Out-of-distribution. (1%)Amir Lukach; Ran Dubin; Amit Dvir; Chen Hajaj
Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumption. (1%)Xuanqi Liu; Zhuotao Liu; Qi Li; Ke Xu; Mingwei Xu
2024-03-16
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples. (98%)Ziqi Zhou; Minghui Li; Wei Liu; Shengshan Hu; Yechao Zhang; Wei Wan; Lulu Xue; Leo Yu Zhang; Dezhong Yang; Hai Jin
Understanding Robustness of Visual State Space Models for Image Classification. (98%)Chengbin Du; Yanxi Li; Chang Xu
Improving Adversarial Transferability of Visual-Language Pre-training Models through Collaborative Multimodal Interaction. (92%)Jiyuan Fu; Zhaoyu Chen; Kaixun Jiang; Haijing Guo; Jiafeng Wang; Shuyong Gao; Wenqiang Zhang
Edge Private Graph Neural Networks with Singular Value Perturbation. (11%)Tingting Tang; Yue Niu; Salman Avestimehr; Murali Annavaram
2024-03-15
Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks. (99%)Chong Wang; Yi Yu; Lanqing Guo; Bihan Wen
Towards Non-Adversarial Algorithmic Recourse. (99%)Tobias Leemann; Martin Pawelczyk; Bardh Prenkaj; Gjergji Kasneci
Time-Frequency Jointed Imperceptible Adversarial Attack to Brainprint Recognition with Deep Learning Models. (99%)Hangjie Yi; Yuhang Ming; Dongjun Liu; Wanzeng Kong
Introducing Adaptive Continuous Adversarial Training (ACAT) to Enhance ML Robustness. (87%)Mohamed elShehaby; Aditya Kotha; Ashraf Matrawy
Revisiting Adversarial Training under Long-Tailed Distributions. (80%)Xinli Yue; Ningping Mou; Qian Wang; Lingchen Zhao
Towards Adversarially Robust Dataset Distillation by Curvature Regularization. (54%)Eric Xue; Yijiang Li; Haoyang Liu; Yifan Shen; Haohan Wang
Interactive Trimming against Evasive Online Data Manipulation Attacks: A Game-Theoretic Approach. (50%)Yue Fu; Qingqing Ye; Rong Du; Haibo Hu
Securing Federated Learning with Control-Flow Attestation: A Novel Framework for Enhanced Integrity and Resilience against Adversarial Attacks. (12%)Zahir Alsulaimawi
Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study. (11%)Chenguang Wang; Ruoxi Jia; Xin Liu; Dawn Song
Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data. (8%)Yuxuan Li; Sarthak Kumar Maharana; Yunhui Guo
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency. (3%)Soumyadeep Pal; Yuguang Yao; Ren Wang; Bingquan Shen; Sijia Liu
Robust Influence-based Training Methods for Noisy Brain MRI. (1%)Minh-Hao Van; Alycia N. Carey; Xintao Wu
2024-03-14
An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models. (99%)Haochen Luo; Jindong Gu; Fengyuan Liu; Philip Torr
Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks. (99%)Roey Bokobza; Yisroel Mirsky
Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency. (98%)Hallgrimur Thorsteinsson; Valdemar J Henriksen; Tong Chen; Raghavendra Selvan
Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement. (83%)Daiwei Yu; Zhuorong Li; Lina Wei; Canghong Jin; Yun Zhang; Sixian Chan
Robust Subgraph Learning by Monitoring Early Training Representations. (80%)Sepideh Neshatfar; Salimeh Yasaei Sekeh
LDPRecover: Recovering Frequencies from Poisoning Attacks against Local Differential Privacy. (76%)Xinyue Sun; Qingqing Ye; Haibo Hu; Jiawei Duan; Tianyu Wo; Jie Xu; Renyu Yang
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting. (74%)Yu Wang; Xiaogeng Liu; Yu Li; Muhao Chen; Chaowei Xiao
Towards White Box Deep Learning. (15%)Maciej Satkiewicz
Symbiotic Game and Foundation Models for Cyber Deception Operations in Strategic Cyber Warfare. (13%)Tao Li; Quanyan Zhu
PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps. (12%)Ruixuan Liu; Tianhao Wang; Yang Cao; Li Xiong
AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Adversarial Visual-Instructions. (2%)Hao Zhang; Wenqi Shao; Hong Liu; Yongqiang Ma; Ping Luo; Yu Qiao; Kaipeng Zhang
Optimistic Verifiable Training by Controlling Hardware Nondeterminism. (1%)Megha Srivastava; Simran Arora; Dan Boneh
Medical Unlearnable Examples: Securing Medical Data from Unauthorized Traning via Sparsity-Aware Local Masking. (1%)Weixiang Sun; Yixin Liu; Zhiling Yan; Kaidi Xu; Lichao Sun
ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks. (1%)Zhaoliang Chen; Zhihao Wu; Ylli Sadikaj; Claudia Plant; Hong-Ning Dai; Shiping Wang; Yiu-Ming Cheung; Wenzhong Guo
2024-03-13
Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation. (92%)Tianyi Chu; Wei Xing; Jiafu Chen; Zhizhong Wang; Jiakai Sun; Lei Zhao; Haibo Chen; Huaizhong Lin
Fast Inference of Removal-Based Node Influence. (54%)Weikai Li; Zhiping Xiao; Xiao Luo; Yizhou Sun
Tastle: Distract Large Language Models for Automatic Jailbreak Attack. (31%)Zeguan Xiao; Yan Yang; Guanhua Chen; Yun Chen
Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack. (8%)Yinggui Wang; Yuanqing Huang; Jianshu Li; Le Yang; Kai Song; Lei Wang
RAF-GI: Towards Robust, Accurate and Fast-Convergent Gradient Inversion Attack in Federated Learning. (2%)Can Liu; Jin Wang; Dongyang Yu
Verifix: Post-Training Correction to Improve Label Noise Robustness with Verified Samples. (1%)Sangamesh Kodge; Deepak Ravikumar; Gobinda Saha; Kaushik Roy
2024-03-12
Versatile Defense Against Adversarial Attacks on Image Recognition. (99%)Haibo Zhang; Zhihua Yao; Kouichi Sakurai
Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation. (61%)Di Mi; Yanjun Zhang; Leo Yu Zhang; Shengshan Hu; Qi Zhong; Haizhuan Yuan; Shirui Pan
Backdoor Attack with Mode Mixture Latent Modification. (8%)Hongwei Zhang; Xiaoyin Xu; Dongsheng An; Xianfeng Gu; Min Zhang
Towards a Framework for Deep Learning Certification in Safety-Critical Applications Using Inherently Safe Design and Run-Time Error Detection. (2%)Romeo Valentin
Duwak: Dual Watermarks in Large Language Models. (2%)Chaoyi Zhu; Jeroen Galjaard; Pin-Yu Chen; Lydia Y. Chen
Visual Privacy Auditing with Diffusion Models. (1%)Kristian Schwethelm; Johannes Kaiser; Moritz Knolle; Daniel Rueckert; Georgios Kaissis; Alexander Ziller
2024-03-11
Intra-Section Code Cave Injection for Adversarial Evasion Attacks on Windows PE Malware File. (99%)Kshitiz Aryal; Maanak Gupta; Mahmoud Abdelsalam; Moustafa Saleh
epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression Recognition. (99%)Batuhan Cengiz; Mert Gulsen; Yusuf H. Sahin; Gozde Unal
PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor. (98%)Jaewon Jung; Hongsun Jang; Jaeyong Song; Jinho Lee
Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification. (97%)Shuai Li; Xiaoguang Ma; Shancheng Jiang; Lu Meng
Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation. (96%)Chengxing Jia; Fuxiang Zhang; Yi-Chen Li; Chen-Xiao Gao; Xu-Hui Liu; Lei Yuan; Zongzhang Zhang; Yang Yu
PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification. (86%)Mert Gulsen; Batuhan Cengiz; Yusuf H. Sahin; Gozde Unal
Overcoming the Paradox of Certified Training with Gaussian Smoothing. (83%)Stefan Balauca; Mark Niklas Müller; Yuhao Mao; Maximilian Baader; Marc Fischer; Martin Vechev
Real is not True: Backdoor Attacks Against Deepfake Detection. (78%)Hong Sun; Ziqiang Li; Lei Liu; Bin Li
Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning. (61%)Fuseinin Mumuni; Alhassan Mumuni
Stealing Part of a Production Language Model. (38%)Nicholas Carlini; Daniel Paleka; Krishnamurthy Dj Dvijotham; Thomas Steinke; Jonathan Hayase; A. Feder Cooper; Katherine Lee; Matthew Jagielski; Milad Nasr; Arthur Conmy; Eric Wallace; David Rolnick; Florian Tramèr
AS-FIBA: Adaptive Selective Frequency-Injection for Backdoor Attack on Deep Face Restoration. (9%)Zhenbo Song; Wenhao Gao; Kaihao Zhang; Wenhan Luo; Zhaoxin Fan; Jianfeng Lu
A novel interface for adversarial trivia question-writing. (3%)Jason Liu
Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation. (2%)Xiaoyang Wang; Huihui Bai; Limin Yu; Yao Zhao; Jimin Xiao
Learning with Noisy Foundation Models. (1%)Hao Chen; Jindong Wang; Zihan Wang; Ran Tao; Hongxin Wei; Xing Xie; Masashi Sugiyama; Bhiksha Raj
DNNShield: Embedding Identifiers for Deep Neural Network Ownership Verification. (1%)Jasper Stang; Torsten Krauß; Alexandra Dmitrienko
2024-03-10
A Zero Trust Framework for Realization and Defense Against Generative AI Attacks in Power Grid. (22%)Md. Shirajum Munir; Sravanthi Proddatoori; Manjushree Muralidhara; Walid Saad; Zhu Han; Sachin Shetty
2024-03-09
Hard-label based Small Query Black-box Adversarial Attack. (99%)Jeonghwan Park; Paul Miller; Niall McLaughlin
IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics. (83%)Ekaterina Shumitskaya; Anastasia Antsiferova; Dmitriy Vatolin
iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself. (82%)Yuhao Bian; Shengjing Tian; Xiuping Liu
Attacking Transformers with Feature Diversity Adversarial Perturbation. (70%)Chenxing Gao; Hang Zhou; Junqing Yu; YuTeng Ye; Jiale Cai; Junle Wang; Wei Yang
2024-03-08
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds. (99%)Tianrui Lou; Xiaojun Jia; Jindong Gu; Li Liu; Siyuan Liang; Bangyan He; Xiaochun Cao
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. (99%)Team Gemini; Petko Georgiev; Ving Ian Lei; Ryan Burnell; Libin Bai; Anmol Gulati; Garrett Tanzer; Damien Vincent; Zhufeng Pan; Shibo Wang; Soroosh Mariooryad; Yifan Ding; Xinyang Geng; Fred Alcober; Roy Frostig; Mark Omernick; Lexi Walker; Cosmin Paduraru; Christina Sorokin; Andrea Tacchetti; Colin Gaffney; Samira Daruki; Olcan Sercinoglu; Zach Gleicher; Juliette Love; Paul Voigtlaender; Rohan Jain; Gabriela Surita; Kareem Mohamed; Rory Blevins; Junwhan Ahn; Tao Zhu; Kornraphop Kawintiranon; Orhan Firat; Yiming Gu; Yujing Zhang; Matthew Rahtz; Manaal Faruqui; Natalie Clay; Justin Gilmer; JD Co-Reyes; Ivo Penchev; Rui Zhu; Nobuyuki Morioka; Kevin Hui; Krishna Haridasan; Victor Campos; Mahdis Mahdieh; Mandy Guo; Samer Hassan; Kevin Kilgour; Arpi Vezer; Heng-Tze Cheng; Liedekerke Raoul de; Siddharth Goyal; Paul Barham; DJ Strouse; Seb Noury; Jonas Adler; Mukund Sundararajan; Sharad Vikram; Dmitry Lepikhin; Michela Paganini; Xavier Garcia; Fan Yang; Dasha Valter; Maja Trebacz; Kiran Vodrahalli; Chulayuth Asawaroengchai; Roman Ring; Norbert Kalb; Livio Baldini Soares; Siddhartha Brahma; David Steiner; Tianhe Yu; Fabian Mentzer; Antoine He; Lucas Gonzalez; Bibo Xu; Raphael Lopez Kaufman; Laurent El Shafey; Junhyuk Oh; Tom Hennigan; George van den Driessche; Seth Odoom; Mario Lucic; Becca Roelofs; Sid Lall; Amit Marathe; Betty Chan; Santiago Ontanon; Luheng He; Denis Teplyashin; Jonathan Lai; Phil Crone; Bogdan Damoc; Lewis Ho; Sebastian Riedel; Karel Lenc; Chih-Kuan Yeh; Aakanksha Chowdhery; Yang Xu; Mehran Kazemi; Ehsan Amid; Anastasia Petrushkina; Kevin Swersky; Ali Khodaei; Gowoon Chen; Chris Larkin; Mario Pinto; Geng Yan; Adria Puigdomenech Badia; Piyush Patil; Steven Hansen; Dave Orr; Sebastien M. R. Arnold; Jordan Grimstad; Andrew Dai; Sholto Douglas; Rishika Sinha; Vikas Yadav; Xi Chen; Elena Gribovskaya; Jacob Austin; Jeffrey Zhao; Kaushal Patel; Paul Komarek; Sophia Austin; Sebastian Borgeaud; Linda Friso; Abhimanyu Goyal; Ben Caine; Kris Cao; Da-Woon Chung; Matthew Lamm; Gabe Barth-Maron; Thais Kagohara; Kate Olszewska; Mia Chen; Kaushik Shivakumar; Rishabh Agarwal; Harshal Godhia; Ravi Rajwar; Javier Snaider; Xerxes Dotiwalla; Yuan Liu; Aditya Barua; Victor Ungureanu; Yuan Zhang; Bat-Orgil Batsaikhan; Mateo Wirth; James Qin; Ivo Danihelka; Tulsee Doshi; Martin Chadwick; Jilin Chen; Sanil Jain; Quoc Le; Arjun Kar; Madhu Gurumurthy; Cheng Li; Ruoxin Sang; Fangyu Liu; Lampros Lamprou; Rich Munoz; Nathan Lintz; Harsh Mehta; Heidi Howard; Malcolm Reynolds; Lora Aroyo; Quan Wang; Lorenzo Blanco; Albin Cassirer; Jordan Griffith; Dipanjan Das; Stephan Lee; Jakub Sygnowski; Zach Fisher; James Besley; Richard Powell; Zafarali Ahmed; Dominik Paulus; David Reitter; Zalan Borsos; Rishabh Joshi; Aedan Pope; Steven Hand; Vittorio Selo; Vihan Jain; Nikhil Sethi; Megha Goel; Takaki Makino; Rhys May; Zhen Yang; Johan Schalkwyk; Christina Butterfield; Anja Hauth; Alex Goldin; Will Hawkins; Evan Senter; Sergey Brin; Oliver Woodman; Marvin Ritter; Eric Noland; Minh Giang; Vijay Bolina; Lisa Lee; Tim Blyth; Ian Mackinnon; Machel Reid; Obaid Sarvana; David Silver; Alexander Chen; Lily Wang; Loren Maggiore; Oscar Chang; Nithya Attaluri; Gregory Thornton; Chung-Cheng Chiu; Oskar Bunyan; Nir Levine; Timothy Chung; Evgenii Eltyshev; Xiance Si; Timothy Lillicrap; Demetra Brady; Vaibhav Aggarwal; Boxi Wu; Yuanzhong Xu; Ross McIlroy; Kartikeya Badola; Paramjit Sandhu; Erica Moreira; Wojciech Stokowiec; Ross Hemsley; Dong Li; Alex Tudor; Pranav Shyam; Elahe Rahimtoroghi; Salem Haykal; Pablo Sprechmann; Xiang Zhou; Diana Mincu; Yujia Li; Ravi Addanki; Kalpesh Krishna; Xiao Wu; Alexandre Frechette; Matan Eyal; Allan Dafoe; Dave Lacey; Jay Whang; Thi Avrahami; Ye Zhang; Emanuel Taropa; Hanzhao Lin; Daniel Toyama; Eliza Rutherford; Motoki Sano; HyunJeong Choe; Alex Tomala; Chalence Safranek-Shrader; Nora Kassner; Mantas Pajarskas; Matt Harvey; Sean Sechrist; Meire Fortunato; Christina Lyu; Gamaleldin Elsayed; Chenkai Kuang; James Lottes; Eric Chu; Chao Jia; Chih-Wei Chen; Peter Humphreys; Kate Baumli; Connie Tao; Rajkumar Samuel; Cicero Nogueira dos Santos; Anders Andreassen; Nemanja Rakićević; Dominik Grewe; Aviral Kumar; Stephanie Winkler; Jonathan Caton; Andrew Brock; Sid Dalmia; Hannah Sheahan; Iain Barr; Yingjie Miao; Paul Natsev; Jacob Devlin; Feryal Behbahani; Flavien Prost; Yanhua Sun; Artiom Myaskovsky; Thanumalayan Sankaranarayana Pillai; Dan Hurt; Angeliki Lazaridou; Xi Xiong; Ce Zheng; Fabio Pardo; Xiaowei Li; Dan Horgan; Joe Stanton; Moran Ambar; Fei Xia; Alejandro Lince; Mingqiu Wang; Basil Mustafa; Albert Webson; Hyo Lee; Rohan Anil; Martin Wicke; Timothy Dozat; Abhishek Sinha; Enrique Piqueras; Elahe Dabir; Shyam Upadhyay; Anudhyan Boral; Lisa Anne Hendricks; Corey Fry; Josip Djolonga; Yi Su; Jake Walker; Jane Labanowski; Ronny Huang; Vedant Misra; Jeremy Chen; RJ Skerry-Ryan; Avi Singh; Shruti Rijhwani; Dian Yu; Alex Castro-Ros; Beer Changpinyo; Romina Datta; Sumit Bagri; Arnar Mar Hrafnkelsson; Marcello Maggioni; Daniel Zheng; Yury Sulsky; Shaobo Hou; Tom Le Paine; Antoine Yang; Jason Riesa; Dominika Rogozinska; Dror Marcus; Dalia El Badawy; Qiao Zhang; Luyu Wang; Helen Miller; Jeremy Greer; Lars Lowe Sjos; Azade Nova; Heiga Zen; Rahma Chaabouni; Mihaela Rosca; Jiepu Jiang; Charlie Chen; Ruibo Liu; Tara Sainath; Maxim Krikun; Alex Polozov; Jean-Baptiste Lespiau; Josh Newlan; Zeyncep Cankara; Soo Kwak; Yunhan Xu; Phil Chen; Andy Coenen; Clemens Meyer; Katerina Tsihlas; Ada Ma; Juraj Gottweis; Jinwei Xing; Chenjie Gu; Jin Miao; Christian Frank; Zeynep Cankara; Sanjay Ganapathy; Ishita Dasgupta; Steph Hughes-Fitt; Heng Chen; David Reid; Keran Rong; Hongmin Fan; Amersfoort Joost van; Vincent Zhuang; Aaron Cohen; Shixiang Shane Gu; Anhad Mohananey; Anastasija Ilic; Taylor Tobin; John Wieting; Anna Bortsova; Phoebe Thacker; Emma Wang; Emily Caveness; Justin Chiu; Eren Sezener; Alex Kaskasoli; Steven Baker; Katie Millican; Mohamed Elhawaty; Kostas Aisopos; Carl Lebsack; Nathan Byrd; Hanjun Dai; Wenhao Jia; Matthew Wiethoff; Elnaz Davoodi; Albert Weston; Lakshman Yagati; Arun Ahuja; Isabel Gao; Golan Pundak; Susan Zhang; Michael Azzam; Khe Chai Sim; Sergi Caelles; James Keeling; Abhanshu Sharma; Andy Swing; YaGuang Li; Chenxi Liu; Carrie Grimes Bostock; Yamini Bansal; Zachary Nado; Ankesh Anand; Josh Lipschultz; Abhijit Karmarkar; Lev Proleev; Abe Ittycheriah; Soheil Hassas Yeganeh; George Polovets; Aleksandra Faust; Jiao Sun; Alban Rrustemi; Pen Li; Rakesh Shivanna; Jeremiah Liu; Chris Welty; Federico Lebron; Anirudh Baddepudi; Sebastian Krause; Emilio Parisotto; Radu Soricut; Zheng Xu; Dawn Bloxwich; Melvin Johnson; Behnam Neyshabur; Justin Mao-Jones; Renshen Wang; Vinay Ramasesh; Zaheer Abbas; Arthur Guez; Constant Segal; Duc Dung Nguyen; James Svensson; Le Hou; Sarah York; Kieran Milan; Sophie Bridgers; Wiktor Gworek; Marco Tagliasacchi; James Lee-Thorp; Michael Chang; Alexey Guseynov; Ale Jakse Hartman; Michael Kwong; Ruizhe Zhao; Sheleem Kashem; Elizabeth Cole; Antoine Miech; Richard Tanburn; Mary Phuong; Filip Pavetic; Sebastien Cevey; Ramona Comanescu; Richard Ives; Sherry Yang; Cosmo Du; Bo Li; Zizhao Zhang; Mariko Iinuma; Clara Huiyi Hu; Aurko Roy; Shaan Bijwadia; Zhenkai Zhu; Danilo Martins; Rachel Saputro; Anita Gergely; Steven Zheng; Dawei Jia; Ioannis Antonoglou; Adam Sadovsky; Shane Gu; Yingying Bi; Alek Andreev; Sina Samangooei; Mina Khan; Tomas Kocisky; Angelos Filos; Chintu Kumar; Colton Bishop; Adams Yu; Sarah Hodkinson; Sid Mittal; Premal Shah; Alexandre Moufarek; Yong Cheng; Adam Bloniarz; Jaehoon Lee; Pedram Pejman; Paul Michel; Stephen Spencer; Vladimir Feinberg; Xuehan Xiong; Nikolay Savinov; Charlotte Smith; Siamak Shakeri; Dustin Tran; Mary Chesus; Bernd Bohnet; George Tucker; Glehn Tamara von; Carrie Muir; Yiran Mao; Hideto Kazawa; Ambrose Slone; Kedar Soparkar; Disha Shrivastava; James Cobon-Kerr; Michael Sharman; Jay Pavagadhi; Carlos Araya; Karolis Misiunas; Nimesh Ghelani; Michael Laskin; David Barker; Qiujia Li; Anton Briukhov; Neil Houlsby; Mia Glaese; Balaji Lakshminarayanan; Nathan Schucher; Yunhao Tang; Eli Collins; Hyeontaek Lim; Fangxiaoyu Feng; Adria Recasens; Guangda Lai; Alberto Magni; Cao Nicola De; Aditya Siddhant; Zoe Ashwood; Jordi Orbay; Mostafa Dehghani; Jenny Brennan; Yifan He; Kelvin Xu; Yang Gao; Carl Saroufim; James Molloy; Xinyi Wu; Seb Arnold; Solomon Chang; Julian Schrittwieser; Elena Buchatskaya; Soroush Radpour; Martin Polacek; Skye Giordano; Ankur Bapna; Simon Tokumine; Vincent Hellendoorn; Thibault Sottiaux; Sarah Cogan; Aliaksei Severyn; Mohammad Saleh; Shantanu Thakoor; Laurent Shefey; Siyuan Qiao; Meenu Gaba; Shuo-yiin Chang; Craig Swanson; Biao Zhang; Benjamin Lee; Paul Kishan Rubenstein; Gan Song; Tom Kwiatkowski; Anna Koop; Ajay Kannan; David Kao; Parker Schuh; Axel Stjerngren; Golnaz Ghiasi; Gena Gibson; Luke Vilnis; Ye Yuan; Felipe Tiengo Ferreira; Aishwarya Kamath; Ted Klimenko; Ken Franko; Kefan Xiao; Indro Bhattacharya; Miteyan Patel; Rui Wang; Alex Morris; Robin Strudel; Vivek Sharma; Peter Choy; Sayed Hadi Hashemi; Jessica Landon; Mara Finkelstein; Priya Jhakra; Justin Frye; Megan Barnes; Matthew Mauger; Dennis Daun; Khuslen Baatarsukh; Matthew Tung; Wael Farhan; Henryk Michalewski; Fabio Viola; Felix de Chaumont Quitry; Charline Le Lan; Tom Hudson; Qingze Wang; Felix Fischer; Ivy Zheng; Elspeth White; Anca Dragan; Jean-baptiste Alayrac; Eric Ni; Alexander Pritzel; Adam Iwanicki; Michael Isard; Anna Bulanova; Lukas Zilka; Ethan Dyer; Devendra Sachan; Srivatsan Srinivasan; Hannah Muckenhirn; Honglong Cai; Amol Mandhane; Mukarram Tariq; Jack W. Rae; Gary Wang; Kareem Ayoub; Nicholas FitzGerald; Yao Zhao; Woohyun Han; Chris Alberti; Dan Garrette; Kashyap Krishnakumar; Mai Gimenez; Anselm Levskaya; Daniel Sohn; Josip Matak; Inaki Iturrate; Michael B. Chang; Jackie Xiang; Yuan Cao; Nishant Ranka; Geoff Brown; Adrian Hutter; Vahab Mirrokni; Nanxin Chen; Kaisheng Yao; Zoltan Egyed; Francois Galilee; Tyler Liechty; Praveen Kallakuri; Evan Palmer; Sanjay Ghemawat; Jasmine Liu; David Tao; Chloe Thornton; Tim Green; Mimi Jasarevic; Sharon Lin; Victor Cotruta; Yi-Xuan Tan; Noah Fiedel; Hongkun Yu; Ed Chi; Alexander Neitz; Jens Heitkaemper; Anu Sinha; Denny Zhou; Yi Sun; Charbel Kaed; Brice Hulse; Swaroop Mishra; Maria Georgaki; Sneha Kudugunta; Clement Farabet; Izhak Shafran; Daniel Vlasic; Anton Tsitsulin; Rajagopal Ananthanarayanan; Alen Carin; Guolong Su; Pei Sun; Shashank V; Gabriel Carvajal; Josef Broder; Iulia Comsa; Alena Repina; William Wong; Warren Weilun Chen; Peter Hawkins; Egor Filonov; Lucia Loher; Christoph Hirnschall; Weiyi Wang; Jingchen Ye; Andrea Burns; Hardie Cate; Diana Gage Wright; Federico Piccinini; Lei Zhang; Chu-Cheng Lin; Ionel Gog; Yana Kulizhskaya; Ashwin Sreevatsa; Shuang Song; Luis C. Cobo; Anand Iyer; Chetan Tekur; Guillermo Garrido; Zhuyun Xiao; Rupert Kemp; Huaixiu Steven Zheng; Hui Li; Ananth Agarwal; Christel Ngani; Kati Goshvadi; Rebeca Santamaria-Fernandez; Wojciech Fica; Xinyun Chen; Chris Gorgolewski; Sean Sun; Roopal Garg; Xinyu Ye; S. M. Ali Eslami; Nan Hua; Jon Simon; Pratik Joshi; Yelin Kim; Ian Tenney; Sahitya Potluri; Lam Nguyen Thiet; Quan Yuan; Florian Luisier; Alexandra Chronopoulou; Salvatore Scellato; Praveen Srinivasan; Minmin Chen; Vinod Koverkathu; Valentin Dalibard; Yaming Xu; Brennan Saeta; Keith Anderson; Thibault Sellam; Nick Fernando; Fantine Huot; Junehyuk Jung; Mani Varadarajan; Michael Quinn; Amit Raul; Maigo Le; Ruslan Habalov; Jon Clark; Komal Jalan; Kalesha Bullard; Achintya Singhal; Thang Luong; Boyu Wang; Sujeevan Rajayogam; Julian Eisenschlos; Johnson Jia; Daniel Finchelstein; Alex Yakubovich; Daniel Balle; Michael Fink; Sameer Agarwal; Jing Li; Dj Dvijotham; Shalini Pal; Kai Kang; Jaclyn Konzelmann; Jennifer Beattie; Olivier Dousse; Diane Wu; Remi Crocker; Chen Elkind; Siddhartha Reddy Jonnalagadda; Jong Lee; Dan Holtmann-Rice; Krystal Kallarackal; Rosanne Liu; Denis Vnukov; Neera Vats; Luca Invernizzi; Mohsen Jafari; Huanjie Zhou; Lilly Taylor; Jennifer Prendki; Marcus Wu; Tom Eccles; Tianqi Liu; Kavya Kopparapu; Francoise Beaufays; Christof Angermueller; Andreea Marzoca; Shourya Sarcar; Hilal Dib; Jeff Stanway; Frank Perbet; Nejc Trdin; Rachel Sterneck; Andrey Khorlin; Dinghua Li; Xihui Wu; Sonam Goenka; David Madras; Sasha Goldshtein; Willi Gierke; Tong Zhou; Yaxin Liu; Yannie Liang; Anais White; Yunjie Li; Shreya Singh; Sanaz Bahargam; Mark Epstein; Sujoy Basu; Li Lao; Adnan Ozturel; Carl Crous; Alex Zhai; Han Lu; Zora Tung; Neeraj Gaur; Alanna Walton; Lucas Dixon; Ming Zhang; Amir Globerson; Grant Uy; Andrew Bolt; Olivia Wiles; Milad Nasr; Ilia Shumailov; Marco Selvi; Francesco Piccinno; Ricardo Aguilar; Sara McCarthy; Misha Khalman; Mrinal Shukla; Vlado Galic; John Carpenter; Kevin Villela; Haibin Zhang; Harry Richardson; James Martens; Matko Bosnjak; Shreyas Rammohan Belle; Jeff Seibert; Mahmoud Alnahlawi; Brian McWilliams; Sankalp Singh; Annie Louis; Wen Ding; Dan Popovici; Lenin Simicich; Laura Knight; Pulkit Mehta; Nishesh Gupta; Chongyang Shi; Saaber Fatehi; Jovana Mitrovic; Alex Grills; Joseph Pagadora; Dessie Petrova; Danielle Eisenbud; Zhishuai Zhang; Damion Yates; Bhavishya Mittal; Nilesh Tripuraneni; Yannis Assael; Thomas Brovelli; Prateek Jain; Mihajlo Velimirovic; Canfer Akbulut; Jiaqi Mu; Wolfgang Macherey; Ravin Kumar; Jun Xu; Haroon Qureshi; Gheorghe Comanici; Jeremy Wiesner; Zhitao Gong; Anton Ruddock; Matthias Bauer; Nick Felt; Anirudh GP; Anurag Arnab; Dustin Zelle; Jonas Rothfuss; Bill Rosgen; Ashish Shenoy; Bryan Seybold; Xinjian Li; Jayaram Mudigonda; Goker Erdogan; Jiawei Xia; Jiri Simsa; Andrea Michi; Yi Yao; Christopher Yew; Steven Kan; Isaac Caswell; Carey Radebaugh; Andre Elisseeff; Pedro Valenzuela; Kay McKinney; Kim Paterson; Albert Cui; Eri Latorre-Chimoto; Solomon Kim; William Zeng; Ken Durden; Priya Ponnapalli; Tiberiu Sosea; Christopher A. Choquette-Choo; James Manyika; Brona Robenek; Harsha Vashisht; Sebastien Pereira; Hoi Lam; Marko Velic; Denese Owusu-Afriyie; Katherine Lee; Tolga Bolukbasi; Alicia Parrish; Shawn Lu; Jane Park; Balaji Venkatraman; Alice Talbert; Lambert Rosique; Yuchung Cheng; Andrei Sozanschi; Adam Paszke; Praveen Kumar; Jessica Austin; Lu Li; Khalid Salama; Wooyeol Kim; Nandita Dukkipati; Anthony Baryshnikov; Christos Kaplanis; XiangHai Sheng; Yuri Chervonyi; Caglar Unlu; Diego de Las Casas; Harry Askham; Kathryn Tunyasuvunakool; Felix Gimeno; Siim Poder; Chester Kwak; Matt Miecnikowski; Vahab Mirrokni; Alek Dimitriev; Aaron Parisi; Dangyi Liu; Tomy Tsai; Toby Shevlane; Christina Kouridi; Drew Garmon; Adrian Goedeckemeyer; Adam R. Brown; Anitha Vijayakumar; Ali Elqursh; Sadegh Jazayeri; Jin Huang; Sara Mc Carthy; Jay Hoover; Lucy Kim; Sandeep Kumar; Wei Chen; Courtney Biles; Garrett Bingham; Evan Rosen; Lisa Wang; Qijun Tan; David Engel; Francesco Pongetti; Cesare Dario de; Dongseong Hwang; Lily Yu; Jennifer Pullman; Srini Narayanan; Kyle Levin; Siddharth Gopal; Megan Li; Asaf Aharoni; Trieu Trinh; Jessica Lo; Norman Casagrande; Roopali Vij; Loic Matthey; Bramandia Ramadhana; Austin Matthews; CJ Carey; Matthew Johnson; Kremena Goranova; Rohin Shah; Shereen Ashraf; Kingshuk Dasgupta; Rasmus Larsen; Yicheng Wang; Manish Reddy Vuyyuru; Chong Jiang; Joana Ijazi; Kazuki Osawa; Celine Smith; Ramya Sree Boppana; Taylan Bilal; Yuma Koizumi; Ying Xu; Yasemin Altun; Nir Shabat; Ben Bariach; Alex Korchemniy; Kiam Choo; Olaf Ronneberger; Chimezie Iwuanyanwu; Shubin Zhao; David Soergel; Cho-Jui Hsieh; Irene Cai; Shariq Iqbal; Martin Sundermeyer; Zhe Chen; Elie Bursztein; Chaitanya Malaviya; Fadi Biadsy; Prakash Shroff; Inderjit Dhillon; Tejasi Latkar; Chris Dyer; Hannah Forbes; Massimo Nicosia; Vitaly Nikolaev; Somer Greene; Marin Georgiev; Pidong Wang; Nina Martin; Hanie Sedghi; John Zhang; Praseem Banzal; Doug Fritz; Vikram Rao; Xuezhi Wang; Jiageng Zhang; Viorica Patraucean; Dayou Du; Igor Mordatch; Ivan Jurin; Lewis Liu; Ayush Dubey; Abhi Mohan; Janek Nowakowski; Vlad-Doru Ion; Nan Wei; Reiko Tojo; Maria Abi Raad; Drew A. Hudson; Vaishakh Keshava; Shubham Agrawal; Kevin Ramirez; Zhichun Wu; Hoang Nguyen; Ji Liu; Madhavi Sewak; Bryce Petrini; DongHyun Choi; Ivan Philips; Ziyue Wang; Ioana Bica; Ankush Garg; Jarek Wilkiewicz; Priyanka Agrawal; Xiaowei Li; Danhao Guo; Emily Xue; Naseer Shaik; Andrew Leach; Sadh MNM Khan; Julia Wiesinger; Sammy Jerome; Abhishek Chakladar; Alek Wenjiao Wang; Tina Ornduff; Folake Abu; Alireza Ghaffarkhah; Marcus Wainwright; Mario Cortes; Frederick Liu; Joshua Maynez; Slav Petrov; Yonghui Wu; Demis Hassabis; Koray Kavukcuoglu; Jeffrey Dean; Oriol Vinyals
Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume. (98%)Ping Guo; Cheng Gong; Xi Lin; Zhiyuan Yang; Qingfu Zhang
Prepared for the Worst: A Learning-Based Adversarial Attack for Resilience Analysis of the ICP Algorithm. (93%)Ziyu Zhang; Johann Laconte; Daniil Lisus; Timothy D. Barfoot
Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples. (93%)Eda Yilmaz; Hacer Yalim Keles
EVD4UAV: An Altitude-Sensitive Benchmark to Evade Vehicle Detection in UAV. (81%)Huiming Sun; Jiacheng Guo; Zibo Meng; Tianyun Zhang; Jianwu Fang; Yuewei Lin; Hongkai Yu
The Impact of Quantization on the Robustness of Transformer-based Text Classifiers. (45%)Seyed Parsa Neshaei; Yasaman Boreshban; Gholamreza Ghassem-Sani; Seyed Abolghasem Mirroshandel
EdgeLeakage: Membership Information Leakage in Distributed Edge Intelligence Systems. (38%)Kongyang Chen; Yi Lin; Hui Luo; Bing Mi; Yatie Xiao; Chao Ma; Jorge Sá Silva
Speech Robust Bench: A Robustness Benchmark For Speech Recognition. (1%)Muhammad A. Shah; David Solans Noguero; Mikko A. Heikkila; Bhiksha Raj; Nicolas Kourtellis
2024-03-07
Defending Against Unforeseen Failure Modes with Latent Adversarial Training. (83%)Stephen Casper; Lennart Schulze; Oam Patel; Dylan Hadfield-Menell
Fooling Neural Networks for Motion Forecasting via Adversarial Attacks. (33%)Edgar Medina; Leyong Loh
Automatic and Universal Prompt Injection Attacks against Large Language Models. (31%)Xiaogeng Liu; Zhiyuan Yu; Yizhe Zhang; Ning Zhang; Chaowei Xiao
ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes. (31%)Hashmat Shadab Malik; Muhammad Huzaifa; Muzammal Naseer; Salman Khan; Fahad Shahbaz Khan
Cell reprogramming design by transfer learning of functional transcriptional networks. (1%)Thomas P. Wytock; Adilson E. Motter
Towards Robustness Analysis of E-Commerce Ranking System. (1%)Ningfei Wang; Yupin Huang; Han Cheng; Jiri Gesi; Xiaojie Wang; Vivek Mittal
2024-03-06
Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectors. (99%)Kalibinuer Tiliwalidi
Improving Adversarial Training using Vulnerability-Aware Perturbation Budget. (99%)Olukorede Fakorede; Modeste Atsague; Jin Tian
Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability. (92%)Rajdeep Haldar; Yue Xing; Qifan Song
Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations. (16%)Xiaolin Sun; Zizhan Zheng
On the Effectiveness of Distillation in Mitigating Backdoors in Pre-trained Encoder. (2%)Tingxu Han; Shenghan Huang; Ziqi Ding; Weisong Sun; Yebo Feng; Chunrong Fang; Jun Li; Hanwei Qian; Cong Wu; Quanjun Zhang; Yang Liu; Zhenyu Chen
Verified Training for Counterfactual Explanation Robustness under Data Shift. (2%)Anna P. Meyer; Yuhao Zhang; Aws Albarghouthi; Loris D'Antoni
2024-03-05
Towards Robust Federated Learning via Logits Calibration on Non-IID Data. (99%)Yu Qiao; Apurba Adhikary; Chaoning Zhang; Choong Seon Hong
Mitigating Label Flipping Attacks in Malicious URL Detectors Using Ensemble Trees. (96%)Ehsan Nowroozi; Nada Jadalla; Samaneh Ghelichkhani; Alireza Jolfaei
Minimum Topology Attacks for Graph Neural Networks. (83%)Mengmei Zhang; Xiao Wang; Chuan Shi; Lingjuan Lyu; Tianchi Yang; Junping Du
Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networks. (82%)Ehsan Nowroozi; Imran Haider; Rahim Taheri; Mauro Conti
A general approach to enhance the survivability of backdoor attacks by decision path coupling. (68%)Yufei Zhao; Dingji Wang; Bihuan Chen; Ziqian Chen; Xin Peng
Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attacks. (61%)Yichang Xu; Ming Yin; Minghong Fang; Neil Zhenqiang Gong
Uplift Modeling for Target User Attacks on Recommender Systems. (12%)Wenjie Wang; Changsheng Wang; Fuli Feng; Wentao Shi; Daizong Ding; Tat-Seng Chua
FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models. (11%)Younghan Lee; Yungi Cho; Woorim Han; Ho Bae; Yunheung Paek
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents. (11%)Qiusi Zhan; Zhixiang Liang; Zifan Ying; Daniel Kang
XAI-Based Detection of Adversarial Attacks on Deepfake Detectors. (8%)Ben Pinhasov; Raz Lapid; Rony Ohayon; Moshe Sipper; Yehudit Aperstein
2024-03-04
Robustness Bounds on the Successful Adversarial Examples: Theory and Practice. (99%)Hiroaki Maeshima; Akira Otsuka
One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models. (99%)Lin Li; Haoyan Guan; Jianing Qiu; Michael Spratling
Improving the Robustness of Object Detection and Classification AI models against Adversarial Patch Attacks. (99%)Roie Kazoom; Raz Birman; Ofer Hadar
COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks. (96%)Zijian Huang; Wenda Chu; Linyi Li; Chejian Xu; Bo Li
Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks. (26%)Sayedeh Leila Noorbakhsh; Binghui Zhang; Yuan Hong; Binghui Wang
BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection. (16%)Yu Chen; Liyan Ma; Liping Jing; Jian Yu
Mirage: Defense against CrossPath Attacks in Software Defined Networks. (3%)Shariq Murtuza; Krishna Asawa
Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation. (1%)Yidong Zhao; Joao Tourais; Iain Pierce; Christian Nitsche; Thomas A. Treibel; Sebastian Weingärtner; Artur M. Schweidtmann; Qian Tao
2024-03-03
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts. (10%)Yijun Yang; Ruiyuan Gao; Xiao Yang; Jianyuan Zhong; Qiang Xu
2024-03-02
SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameters. (99%)Jiahao Cui; Jiale Duan; Binyan Luo; Hang Cao; Wang Guo; Haifeng Li
Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy. (68%)Jamie Hayes; Ilia Shumailov; Eleni Triantafillou; Amr Khalifa; Nicolas Papernot
Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models. (56%)Arijit Ghosh Chowdhury; Md Mofijul Islam; Vaibhav Kumar; Faysal Hossain Shezan; Vaibhav Kumar; Vinija Jain; Aman Chadha
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks. (31%)Yifan Zeng; Yiran Wu; Xiao Zhang; Huazheng Wang; Qingyun Wu
Adversarial Testing for Visual Grounding via Image-Aware Property Reduction. (11%)Zhiyuan Chang; Mingyang Li; Junjie Wang; Cheng Li; Boyu Wu; Fanjiang Xu; Qing Wang
Query Recovery from Easy to Hard: Jigsaw Attack against SSE. (2%)Hao Nie; Wei Wang; Peng Xu; Xianglong Zhang; Laurence T. Yang; Kaitai Liang
Accelerating Greedy Coordinate Gradient via Probe Sampling. (1%)Yiran Zhao; Wenyue Zheng; Tianle Cai; Xuan Long Do; Kenji Kawaguchi; Anirudh Goyal; Michael Shieh
2024-03-01
Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey. (91%)Lucas Schott; Josephine Delas; Hatem Hajri; Elies Gherbi; Reda Yaich; Nora Boulahia-Cuppens; Frederic Cuppens; Sylvain Lamprier
Resilience of Entropy Model in Distributed Neural Networks. (67%)Milin Zhang; Mohammad Abdi; Shahriar Rifat; Francesco Restuccia
Attacking Delay-based PUFs with Minimal Adversary Model. (45%)Hongming Fei; Owen Millwood; Prosanta Gope; Jack Miskelly; Biplab Sikdar
2024-02-29
Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification. (99%)Sonal Joshi; Thomas Thebaud; Jesús Villalba; Najim Dehak
How to Train your Antivirus: RL-based Hardening through the Problem-Space. (99%)Jacopo Cortellazzi; Ilias Tsingenopoulos; Branislav Bošanský; Simone Aonzo; Davy Preuveneers; Wouter Joosen; Fabio Pierazzi; Lorenzo Cavallaro
On Robustness and Generalization of ML-Based Congestion Predictors to Valid and Imperceptible Perturbations. (88%)Chester Holtz; Yucheng Wang; Chung-Kuan Cheng; Bill Lin
Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials. (76%)Gennaro Nolano; Moritz Blum; Basil Ell; Philipp Cimiano
Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance. (38%)Huakun Shen; Boyue Caroline Hu; Krzysztof Czarnecki; Lina Marsso; Marsha Chechik
Verification of Neural Networks' Global Robustness. (38%)Anan Kabaha; Dana Drachsler-Cohen
SynGhost: Imperceptible and Universal Task-agnostic Backdoor Attack in Pre-trained Language Models. (16%)Pengzhou Cheng; Wei Du; Zongru Wu; Fengwei Zhang; Libo Chen; Gongshen Liu
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge. (2%)Ansh Arora; Xuanli He; Maximilian Mozes; Srinibas Swain; Mark Dras; Qiongkai Xu
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes. (1%)Xiaomeng Hu; Pin-Yu Chen; Tsung-Yi Ho
Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model. (1%)Hao Cheng; Erjia Xiao; Jindong Gu; Le Yang; Jinhao Duan; Jize Zhang; Jiahang Cao; Kaidi Xu; Renjing Xu
2024-02-28
Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense. (99%)Qiao Han; yong huang; xinling Guo; Yiteng Zhai; Yu Qin; Yao Yang
MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks. (99%)Fangyuan Zhang; Huichi Zhou; Shuangjiao Li; Hongtao Wang
Catastrophic Overfitting: A Potential Blessing in Disguise. (98%)Mengnan Zhao; Lihe Zhang; Yuqiu Kong; Baocai Yin
Living-off-The-Land Reverse-Shell Detection by Informed Data Augmentation. (76%)Dmitrijs Trizna; Luca Demetrio; Battista Biggio; Fabio Roli
A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems. (64%)Fangzhou Wu; Ning Zhang; Somesh Jha; Patrick McDaniel; Chaowei Xiao
Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction. (33%)Tong Liu; Yingjie Zhang; Zhe Zhao; Yinpeng Dong; Guozhu Meng; Kai Chen
Out-of-Distribution Detection using Neural Activation Prior. (1%)Weilin Wan; Weizhong Zhang; Cheng Jin
2024-02-27
Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates. (99%)Daniele Angioni; Luca Demetrio; Maura Pintor; Luca Oneto; Davide Anguita; Battista Biggio; Fabio Roli
Extreme Miscalibration and the Illusion of Adversarial Robustness. (99%)Vyas Raina; Samson Tan; Volkan Cevher; Aditya Rawal; Sheng Zha; George Karypis
Black-box Adversarial Attacks Against Image Quality Assessment Models. (99%)Yu Ran; Ao-Xiang Zhang; Mingjie Li; Weixuan Tang; Yuan-Gen Wang
Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks. (99%)Zhewei Wu; Ruilong Yu; Qihe Liu; Shuying Cheng; Shilin Qiu; Shijie Zhou
LLM-Resistant Math Word Problem Generation via Adversarial Attacks. (87%)Roy Xie; Chengxuan Huang; Junlin Wang; Bhuwan Dhingra
Breaking the Black-Box: Confidence-Guided Model Inversion Attack for Distribution Shift. (83%)Xinhao Liu; Yingzhao Jiang; Zetao Lin
Model X-ray:Detecting Backdoored Models via Decision Boundary. (67%)Yanghao Su; Jie Zhang; Ting Xu; Tianwei Zhang; Weiming Zhang; Nenghai Yu
Towards Fairness-Aware Adversarial Learning. (11%)Yanghao Zhang; Tianle Zhang; Ronghui Mu; Xiaowei Huang; Wenjie Ruan
Time-Restricted Double-Spending Attack on PoW-based Blockchains. (1%)Yiming Jiang; Jiangfan Zhang
2024-02-26
Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing. (99%)Kefu Guo; Fengfan Zhou; Hefei Ling; Ping Li; Hui Liu
Improving behavior based authentication against adversarial attack using XAI. (99%)Dong Qin; George Amariucai; Daji Qiao; Yong Guan
Adversarial example soups: averaging multiple adversarial examples improves transferability without increasing additional generation time. (99%)Bo Yang; Hengwei Zhang; Chenwei Li; Jindong Wang
A Curious Case of Remarkable Resilience to Gradient Attacks via Fully Convolutional and Differentiable Front End with a Skip Connection. (98%)Leonid Boytsov; Ameya Joshi; Filipe Condessa
Adversarial Perturbations of Physical Signals. (92%)Robert L. Bassett; Dellen Austin Van; Anthony P. Austin
Unveiling Vulnerability of Self-Attention. (87%)Khai Jiet Liong; Hongqiu Wu; Hai Zhao
Edge Detectors Can Make Deep Convolutional Neural Networks More Robust. (83%)Jin Ding; Jie-Chao Zhao; Yong-Zhi Sun; Ping Tan; Jia-Wei Wang; Ji-En Ma; You-Tong Fang
Investigating Deep Watermark Security: An Adversarial Transferability Perspective. (64%)Biqing Qi; Junqi Gao; Yiang Luo; Jianxing Liu; Ligang Wu; Bowen Zhou
Defending LLMs against Jailbreaking Attacks via Backtranslation. (64%)Yihan Wang; Zhouxing Shi; Andrew Bai; Cho-Jui Hsieh
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts. (56%)Mikayel Samvelyan; Sharath Chandra Raparthy; Andrei Lupu; Eric Hambro; Aram H. Markosyan; Manish Bhatt; Yuning Mao; Minqi Jiang; Jack Parker-Holder; Jakob Foerster; Tim Rocktäschel; Roberta Raileanu
Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models. (50%)Jeffrey G. Wang; Jason Wang; Marvin Li; Seth Neel
WIPI: A New Web Threat for LLM-Driven Web Agents. (8%)Fangzhou Wu; Shutong Wu; Yulong Cao; Chaowei Xiao
RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions. (4%)Yuansen Zhang; Xiao Wang; Zhiheng Xi; Han Xia; Tao Gui; Qi Zhang; Xuanjing Huang
An Innovative Information Theory-based Approach to Tackle and Enhance The Transparency in Phishing Detection. (1%)Van Nguyen; Tingmin Wu; Xingliang Yuan; Marthie Grobler; Surya Nepal; Carsten Rudolph
2024-02-25
From Noise to Clarity: Unraveling the Adversarial Suffix of Large Language Model Attacks via Translation of Text Embeddings. (98%)Hao Wang; Hao Li; Minlie Huang; Lei Sha
An Adversarial Robustness Benchmark for Enterprise Network Intrusion Detection. (92%)João Vitorino; Miguel Silva; Eva Maia; Isabel Praça
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing. (76%)Jiabao Ji; Bairu Hou; Alexander Robey; George J. Pappas; Hamed Hassani; Yang Zhang; Eric Wong; Shiyu Chang
Adversarial-Robust Transfer Learning for Medical Imaging via Domain Assimilation. (73%)Xiaohui Chen; Tie Luo
Evaluating Robustness of Generative Search Engine on Adversarial Factual Questions. (13%)Xuming Hu; Xiaochuan Li; Junzhe Chen; Yinghui Li; Yangning Li; Xiaoguang Li; Yasheng Wang; Qun Liu; Lijie Wen; Philip S. Yu; Zhijiang Guo
DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers. (2%)Xirui Li; Ruochen Wang; Minhao Cheng; Tianyi Zhou; Cho-Jui Hsieh
State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey. (1%)Chaoyu Zhang
m2mKD: Module-to-Module Knowledge Distillation for Modular Transformers. (1%)Ka Man Lo; Yiming Liang; Wenyu Du; Yuantao Fan; Zili Wang; Wenhao Huang; Lei Ma; Jie Fu
2024-02-24
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails. (87%)Neal Mangaokar; Ashish Hooda; Jihye Choi; Shreyas Chandrashekaran; Kassem Fawaz; Somesh Jha; Atul Prakash
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper. (86%)Daoyuan Wu; Shuai Wang; Yang Liu; Ning Liu
RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation. (82%)Jiawei Zhou; Linye Lyu; Daojing He; Yu Li
Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks. (76%)Zhiying Jiang; Xingyuan Li; Jinyuan Liu; Xin Fan; Risheng Liu
Optimal Zero-Shot Detector for Multi-Armed Attacks. (50%)Federica Granese; Marco Romanelli; Pablo Piantanida
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning. (1%)Yong Liu; Zirui Zhu; Chaoyu Gong; Minhao Cheng; Cho-Jui Hsieh; Yang You
2024-02-23
Distilling Adversarial Robustness Using Heterogeneous Teachers. (99%)Jieren Deng; Aaron Palmer; Rigel Mahmood; Ethan Rathbun; Jinbo Bi; Kaleel Mahmood; Derek Aguiar
Fast Adversarial Attacks on Language Models In One GPU Minute. (98%)Vinu Sankar Sadasivan; Shoumik Saha; Gaurang Sriramanan; Priyatham Kattakinda; Atoosa Chegini; Soheil Feizi
A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing. (98%)Daniel Gibert; Giulio Zizzo; Quan Le; Jordi Planes
ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation. (93%)Yi Zhang; Yun Tang; Wenjie Ruan; Xiaowei Huang; Siddartha Khastgir; Paul Jennings; Xingyu Zhao
On the Duality Between Sharpness-Aware Minimization and Adversarial Training. (92%)Yihao Zhang; Hangzhou He; Jingyu Zhu; Huanran Chen; Yifei Wang; Zeming Wei
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm. (87%)Yanqi Qiao; Dazhuang Liu; Rui Wang; Kaitai Liang
Deep Networks Always Grok and Here is Why. (76%)Ahmed Imtiaz Humayun; Randall Balestriero; Richard Baraniuk
BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators. (67%)Yu Tian; Xiao Yang; Yinpeng Dong; Heming Yang; Hang Su; Jun Zhu
Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods. (61%)Zheyu Zhang
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement. (5%)Heegyu Kim; Sehyun Yuk; Hyunsouk Cho
Prime+Retouch: When Cache is Locked and Leaked. (2%)Jaehyuk Lee; Fan Sang; Taesoo Kim
TREC: APT Tactic / Technique Recognition via Few-Shot Provenance Subgraph Learning. (1%)Mingqi Lv; HongZhe Gao; Xuebo Qiu; Tieming Chen; Tiantian Zhu; Jinyin Chen; Shouling Ji
2024-02-22
SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge. (99%)Lucas Fenaux; Florian Kerschbaum
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off. (98%)Futa Waseda; Ching-Chun Chang; Isao Echizen
Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images. (93%)Zefeng Wang; Zhen Han; Shuo Chen; Fan Xue; Zifeng Ding; Xun Xiao; Volker Tresp; Philip Torr; Jindong Gu
Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task. (83%)Jinxu Zhao; Guanting Dong; Yueyan Qiu; Tingfeng Hui; Xiaoshuai Song; Daichi Guo; Weiran Xu
Mitigating Fine-tuning Jailbreak Attack with Backdoor Enhanced Alignment. (75%)Jiongxiao Wang; Jiazhao Li; Yiquan Li; Xiangyu Qi; Junjie Hu; Yixuan Li; Patrick McDaniel; Muhao Chen; Bo Li; Chaowei Xiao
Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models. (26%)Zachary Horvitz; Jingru Chen; Rahul Aditya; Harshvardhan Srivastava; Robert West; Zhou Yu; Kathleen McKeown
2024-02-21
AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning. (99%)Vasudev Gohil; Satwik Patnaik; Dileep Kalathil; Jeyavijayan Rajendran
A Simple and Yet Fairly Effective Defense for Graph Neural Networks. (98%)Sofiane Ennadir; Yassine Abbahaddou; Johannes F. Lutzeyer; Michalis Vazirgiannis; Henrik Boström
Adversarial Purification and Fine-tuning for Robust UDC Image Restoration. (98%)Zhenbo Song; Zhenyuan Zhang; Kaihao Zhang; Wenhan Luo; Zhaoxin Fan; Jianfeng Lu
Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment. (83%)Vyas Raina; Adian Liusie; Mark Gales
Robustness of Deep Neural Networks for Micro-Doppler Radar Classification. (80%)Mikolaj Czerkawski; Carmine Clemente; Craig MichieCraig Michie; Christos Tachtatzis
Flexible Physical Camouflage Generation Based on a Differential Approach. (38%)Yang Li; Wenyi Tan; Chenxing Zhao; Shuangju Zhou; Xinkai Liang; Quan Pan
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models. (10%)Jiawei Liang; Siyuan Liang; Man Luo; Aishan Liu; Dongchen Han; Ee-Chien Chang; Xiaochun Cao
Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs. (8%)Xiaoxia Li; Siyuan Liang; Jiyi Zhang; Han Fang; Aishan Liu; Ee-Chien Chang
Coercing LLMs to do and reveal (almost) anything. (4%)Jonas Geiping; Alex Stein; Manli Shu; Khalid Saifullah; Yuxin Wen; Tom Goldstein
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching. (1%)Zizheng Pan; Bohan Zhuang; De-An Huang; Weili Nie; Zhiding Yu; Chaowei Xiao; Jianfei Cai; Anima Anandkumar
2024-02-20
QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems. (92%)Jinjing Shi; Zimeng Xiao; Heyuan Shi; Yu Jiang; Xuelong Li
Defending Jailbreak Prompts via In-Context Adversarial Game. (76%)Yujun Zhou; Yufei Han; Haomin Zhuang; Taicheng Guo; Kehan Guo; Zhenwen Liang; Hongyan Bao; Xiangliang Zhang
Round Trip Translation Defence against Large Language Model Jailbreaking Attacks. (74%)Canaan Yung; Hadi Mohaghegh Dolatabadi; Sarah Erfani; Christopher Leckie
Investigating the Impact of Model Instability on Explanations and Uncertainty. (69%)Sara Vera Marjanović; Isabelle Augenstein; Christina Lioma
A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models. (68%)Zihao Xu; Yi Liu; Gelei Deng; Yuekang Li; Stjepan Picek
Learning to Poison Large Language Models During Instruction Tuning. (13%)Yao Qiang; Xiangyu Zhou; Saleh Zare Zade; Mohammad Amin Roshani; Douglas Zytko; Dongxiao Zhu
Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits. (3%)Zhiwei Wang; Huazheng Wang; Hongning Wang
The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative. (1%)Zhen Tan; Chengshuai Zhao; Raha Moraffah; Yifan Li; Yu Kong; Tianlong Chen; Huan Liu
RITFIS: Robust input testing framework for LLMs-based intelligent software. (1%)Mingxuan Xiao; Yan Xiao; Hai Dong; Shunhui Ji; Pengcheng Zhang
2024-02-19
Query-Based Adversarial Prompt Generation. (99%)Jonathan Hayase; Ema Borevkovic; Nicholas Carlini; Florian Tramèr; Milad Nasr
Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training. (99%)Leo Hyun Park; Jaeuk Kim; Myung Gyo Oh; Jaewoo Park; Taekyoung Kwon
AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization. (99%)Jiyao Li; Mingze Ni; Yifei Dong; Tianqing Zhu; Wei Liu
An Adversarial Approach to Evaluating the Robustness of Event Identification Models. (98%)Obai Bahwal; Oliver Kosut; Lalitha Sankar
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies. (97%)Xiangyu Liu; Chenghao Deng; Yanchao Sun; Yongyuan Liang; Furong Huang
Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels. (92%)Shubhi Shukla; Manaar Alam; Pabitra Mitra; Debdeep Mukhopadhyay
Attacks on Node Attributes in Graph Neural Networks. (83%)Ying Xu; Michael Lanier; Anindya Sarkar; Yevgeniy Vorobeychik
Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors. (68%)Yiwei Lu; Matthew Y. R. Yang; Gautam Kamath; Yaoliang Yu
Self-Guided Robust Graph Structure Refinement. (67%)Yeonjun In; Kanghoon Yoon; Kibum Kim; Kijung Shin; Chanyoung Park
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models. (50%)Christian Schlarmann; Naman Deep Singh; Francesco Croce; Matthias Hein
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning. (15%)Shuai Zhao; Leilei Gan; Luu Anh Tuan; Jie Fu; Lingjuan Lyu; Meihuizi Jia; Jinming Wen
Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overview. (1%)Alexander Auras; Kanchana Vaishnavi Gandikota; Hannah Droege; Michael Moeller
Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships. (1%)Myung Gyo Oh; Hong Eun Ahn; Leo Hyun Park; Taekyoung Kwon
Privacy-Preserving Low-Rank Adaptation for Latent Diffusion Models. (1%)Zihao Luo; Xilie Xu; Feng Liu; Yun Sing Koh; Di Wang; Jingfeng Zhang
2024-02-18
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models. (93%)Cuong Dang; Dung D. Le; Thai Le
Evaluating Adversarial Robustness of Low dose CT Recovery. (92%)Kanchana Vaishnavi Gandikota; Paramanand Chandramouli; Hannah Droege; Michael Moeller
Evaluating Efficacy of Model Stealing Attacks and Defenses on Quantum Neural Networks. (83%)Satwik Kundu; Debarshi Kundu; Swaroop Ghosh
The Effectiveness of Random Forgetting for Robust Generalization. (75%)Vijaya Raghavan T Ramkumar; Bahram Zonooz; Elahe Arani
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection. (26%)Jiawei Liang; Siyuan Liang; Aishan Liu; Xiaojun Jia; Junhao Kuang; Xiaochun Cao
Poisoning Federated Recommender Systems with Fake Users. (5%)Ming Yin; Yichang Xu; Minghong Fang; Neil Zhenqiang Gong
SPML: A DSL for Defending Language Models Against Prompt Attacks. (1%)Reshabh K Sharma; Vinayak Gupta; Dan Grossman
Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge Distillation. (1%)Hyunjune Shin; Dong-Wan Choi
2024-02-17
Maintaining Adversarial Robustness in Continuous Learning. (75%)Xiaolei Ru; Xiaowei Cao; Zijia Liu; Jack Murdoch Moore; Xin-Ya Zhang; Xia Zhu; Wenjia Wei; Gang Yan
Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning. (22%)Hadi M. Dolatabadi; Sarah M. Erfani; Christopher Leckie
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents. (8%)Wenkai Yang; Xiaohan Bi; Yankai Lin; Sishuo Chen; Jie Zhou; Xu Sun
VoltSchemer: Use Voltage Noise to Manipulate Your Wireless Charger. (2%)Zihao Zhan; Yirui Yang; Haoqi Shan; Hanqiu Wang; Yier Jin; Shuo Wang
2024-02-16
DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation. (99%)Yunjuan Wang; Hussein Hazimeh; Natalia Ponomareva; Alexey Kurakin; Ibrahim Hammoud; Raman Arora
Theoretical Understanding of Learning from Adversarial Perturbations. (98%)Soichiro Kumano; Hiroshi Kera; Toshihiko Yamasaki
Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks. (98%)R. Patrick Xian; Alex J. Lee; Satvik Lolla; Vincent Wang; Qiming Cui; Russell Ro; Reza Abbasi-Asl
VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models. (92%)Ziyi Yin; Muchao Ye; Tianrong Zhang; Jiaqi Wang; Han Liu; Jinghui Chen; Ting Wang; Fenglong Ma
The AI Security Pyramid of Pain. (47%)Chris M. Ward; Josh Harguess; Julia Tao; Daniel Christman; Paul Spicer; Mike Tan
AIM: Automated Input Set Minimization for Metamorphic Security Testing. (2%)Nazanin Bayati Chaleshtari; Yoann Marquer; Fabrizio Pastore; Lionel C. Briand
Universal Prompt Optimizer for Safe Text-to-Image Generation. (1%)Zongyu Wu; Hongcheng Gao; Yueze Wang; Xiang Zhang; Suhang Wang
ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detection. (1%)Fan Huang; Haewoon Kwak; Jisun An
2024-02-15
Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks. (62%)Álvaro Huertas-García; Alejandro Martín; Javier Huertas-Tato; David Camacho
On the Safety Concerns of Deploying LLMs/VLMs in Robotics: Highlighting the Risks and Vulnerabilities. (31%)Xiyang Wu; Ruiqi Xian; Tianrui Guan; Jing Liang; Souradip Chakraborty; Fuxiao Liu; Brian Sadler; Dinesh Manocha; Amrit Singh Bedi
Backdoor Attack against One-Class Sequential Anomaly Detection Models. (9%)He Cheng; Shuhan Yuan
A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents. (5%)Lingbo Mo; Zeyi Liao; Boyuan Zheng; Yu Su; Chaowei Xiao; Huan Sun
FedRDF: A Robust and Dynamic Aggregation Function against Poisoning Attacks in Federated Learning. (3%)Enrique Mármol Campos; Aurora González Vidal; José Luis Hernández Ramos; Antonio Skarmeta
Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks. (1%)Jun-Jie Zhang; Deyu Meng
2024-02-14
Exploring the Adversarial Capabilities of Large Language Models. (98%)Lukas Struppek; Minh Hieu Le; Dominik Hintersdorf; Kristian Kersting
PAL: Proxy-Guided Black-Box Attack on Large Language Models. (92%)Chawin Sitawarin; Norman Mu; David Wagner; Alexandre Araujo
Only My Model On My Data: A Privacy Preserving Approach Protecting one Model and Deceiving Unauthorized Black-Box Models. (92%)Weiheng Chai; Brian Testa; Huantao Ren; Asif Salekin; Senem Velipasalar
How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments? (80%)Congcong Wen; Jiazhao Liang; Shuaihang Yuan; Hao Huang; Yi Fang
Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems. (76%)Shiyi Yang; Lina Yao; Chen Wang; Xiwei Xu; Liming Zhu
Attacking Large Language Models with Projected Gradient Descent. (67%)Simon Geisler; Tom Wollschläger; M. H. I. Abdalla; Johannes Gasteiger; Stephan Günnemann
Detecting Adversarial Spectrum Attacks via Distance to Decision Boundary Statistics. (47%)Wenwei Zhao; Xiaowen Li; Shangqing Zhao; Jie Xu; Yao Liu; Zhuo Lu
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding. (38%)Zhangchen Xu; Fengqing Jiang; Luyao Niu; Jinyuan Jia; Bill Yuchen Lin; Radha Poovendran
Reward Poisoning Attack Against Offline Reinforcement Learning. (12%)Yinglun Xu; Rohan Gumaste; Gagandeep Singh
Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model Customization. (9%)Rui Zhang; Hongwei Li; Rui Wen; Wenbo Jiang; Yuan Zhang; Michael Backes; Yun Shen; Yang Zhang
Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation. (3%)Jessica Quaye; Alicia Parrish; Oana Inel; Charvi Rastogi; Hannah Rose Kirk; Minsuk Kahng; Liemt Erin van; Max Bartolo; Jess Tsang; Justin White; Nathan Clement; Rafael Mosquera; Juan Ciro; Vijay Janapa Reddi; Lora Aroyo
Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling. (2%)Yuhui Shi; Qiang Sheng; Juan Cao; Hao Mi; Beizhe Hu; Danding Wang
Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks. (1%)Yixin Cheng; Markos Georgopoulos; Volkan Cevher; Grigorios G. Chrysos
Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption. (1%)Chenlu Ye; Jiafan He; Quanquan Gu; Tong Zhang
Immediate generalisation in humans but a generalisation lag in deep neural networks$\unicode{x2014}$evidence for representational divergence? (1%)Lukas S. Huber; Fred W. Mast; Felix A. Wichmann
Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues. (1%)Zhiyuan Chang; Mingyang Li; Yi Liu; Junjie Wang; Qing Wang; Yang Liu
2024-02-13
Faster Repeated Evasion Attacks in Tree Ensembles. (96%)Lorenzo Cascioli; Laurens Devos; Ondřej Kuželka; Jesse Davis
Generating Universal Adversarial Perturbations for Quantum Classifiers. (93%)Gautham Anil; Vishnu Vinod; Apurva Narayan
Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks. (83%)Qiyuan An; Christos Sevastopoulos; Fillia Makedon
Data Reconstruction Attacks and Defenses: A Systematic Evaluation. (76%)Sheng Liu; Zihan Wang; Qi Lei
COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability. (62%)Xingang Guo; Fangxu Yu; Huan Zhang; Lianhui Qin; Bin Hu
Test-Time Backdoor Attacks on Multimodal Large Language Models. (56%)Dong Lu; Tianyu Pang; Chao Du; Qian Liu; Xianjun Yang; Min Lin
Adversarially Robust Feature Learning for Breast Cancer Diagnosis. (33%)Degan Hao; Dooman Arefan; Margarita Zuley; Wendie Berg; Shandong Wu
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast. (31%)Xiangming Gu; Xiaosen Zheng; Tianyu Pang; Chao Du; Qian Liu; Ye Wang; Jing Jiang; Min Lin
Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing. (10%)Alaa Anani; Tobias Lorenz; Bernt Schiele; Mario Fritz
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation. (1%)Xuexin Chen; Ruichu Cai; Zhengting Huang; Yuxuan Zhu; Julien Horwood; Zhifeng Hao; Zijian Li; Jose Miguel Hernandez-Lobato
2024-02-12
Understanding Deep Learning defenses Against Adversarial Examples Through Visualizations for Dynamic Risk Assessment. (99%)Xabier Echeberria-Barrio; Amaia Gil-Lerchundi; Jon Egana-Zubia; Raul Orduna-Urrutia
Topological safeguard for evasion attack interpreting the neural networks' behavior. (89%)Xabier Echeberria-Barrio; Amaia Gil-Lerchundi; Iñigo Mendialdua; Raul Orduna-Urrutia
PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models. (83%)Wei Zou; Runpeng Geng; Binghui Wang; Jinyuan Jia
Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experience. (33%)Ethan Wilson; Azim Ibragimov; Michael J. Proulx; Sai Deep Tetali; Kevin Butler; Eakta Jain
OrderBkd: Textual backdoor attack through repositioning. (13%)Irina Alekseevskaia; Konstantin Arkhipenko
Tighter Bounds on the Information Bottleneck with Application to Deep Learning. (10%)Nir Weingarten; Zohar Yakhini; Moshe Butman; Ran Gilad-Bachrach
Multi-Attribute Vision Transformers are Efficient and Robust Learners. (9%)Hanan Gani; Nada Saadi; Noor Hussein; Karthik Nandakumar
Customizable Perturbation Synthesis for Robust SLAM Benchmarking. (9%)Xiaohao Xu; Tianyi Zhang; Sibo Wang; Xiang Li; Yongqi Chen; Ye Li; Bhiksha Raj; Matthew Johnson-Roberson; Xiaonan Huang
THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation. (5%)Wilbert Pumacay; Ishika Singh; Jiafei Duan; Ranjay Krishna; Jesse Thomason; Dieter Fox
Accelerated Smoothing: A Scalable Approach to Randomized Smoothing. (3%)Devansh Bhardwaj; Kshitiz Kaushik; Sarthak Gupta
Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors. (3%)Dinuka Sahabandu; Xiaojun Xu; Arezoo Rajabi; Luyao Niu; Bhaskar Ramasubramanian; Bo Li; Radha Poovendran
Local Centrality Minimization with Quality Guarantees. (1%)Atsushi Miyauchi; Lorenzo Severini; Francesco Bonchi
NeuralSentinel: Safeguarding Neural Network Reliability and Trustworthiness. (1%)Xabier Echeberria-Barrio; Mikel Gorricho; Selene Valencia; Francesco Zola
Do Membership Inference Attacks Work on Large Language Models? (1%)Michael Duan; Anshuman Suri; Niloofar Mireshghallah; Sewon Min; Weijia Shi; Luke Zettlemoyer; Yulia Tsvetkov; Yejin Choi; David Evans; Hannaneh Hajishirzi
Pixel Sentence Representation Learning. (1%)Chenghao Xiao; Zhuoxu Huang; Danlu Chen; G Thomas Hudson; Yizhi Li; Haoran Duan; Chenghua Lin; Jie Fu; Jungong Han; Noura Al Moubayed
2024-02-11
A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense. (99%)Ryota Iijima; Sayaka Shiota; Hitoshi Kiya
Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble. (98%)Yunzhe Xue; Usman Roshan
2024-02-10
Whispers in the Machine: Confidentiality in LLM-integrated Systems. (26%)Jonathan Evertz; Merlin Chlosta; Lea Schönherr; Thorsten Eisenhofer
Architectural Neural Backdoors from First Principles. (26%)Harry Langford; Ilia Shumailov; Yiren Zhao; Robert Mullins; Nicolas Papernot
2024-02-09
Anomaly Unveiled: Securing Image Classification against Adversarial Patch Attacks. (98%)Nandish Chattopadhyay; Amira Guesmi; Muhammad Shafique
Fight Back Against Jailbreaking via Prompt Adversarial Tuning. (95%)Yichuan Mo; Yuji Wang; Zeming Wei; Yisen Wang
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations. (84%)Enyi Jiang; Gagandeep Singh
System-level Analysis of Adversarial Attacks and Defenses on Intelligence in O-RAN based Cellular Networks. (82%)Azuka Chiejina; Brian Kim; Kaushik Chowhdury; Vijay K. Shah
The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks. (70%)Jona te Lintelo; Stefanos Koffas; Stjepan Picek
Corruption Robust Offline Reinforcement Learning with Human Feedback. (67%)Debmalya Mandal; Andi Nika; Parameswaran Kamalaruban; Adish Singla; Goran Radanović
Quantifying and Enhancing Multi-modal Robustness with Modality Preference. (56%)Zequn Yang; Yake Wei; Ce Liang; Di Hu
StruQ: Defending Against Prompt Injection with Structured Queries. (45%)Sizhe Chen; Julien Piet; Chawin Sitawarin; David Wagner
Evaluating Membership Inference Attacks and Defenses in Federated Learning. (4%)Gongxi Zhu; Donghao Li; Hanlin Gu; Yuxing Han; Yuan Yao; Lixin Fan; Qiang Yang
Blockchain Bribing Attacks and the Efficacy of Counterincentives. (1%)Dimitris Karakostas; Aggelos Kiayias; Thomas Zacharias
For Better or For Worse? Learning Minimum Variance Features With Label Augmentation. (1%)Muthu Chidambaram; Rong Ge
2024-02-08
Comprehensive Assessment of Jailbreak Attacks Against LLMs. (99%)Junjie Chu; Yugeng Liu; Ziqing Yang; Xinyue Shen; Michael Backes; Yang Zhang
Investigating White-Box Attacks for On-Device Models. (93%)Mingyi Zhou; Xiang Gao; Jing Wu; Kui Liu; Hailong Sun; Li Li
TETRIS: Towards Exploring the Robustness of Interactive Segmentation. (81%)Andrey Moskalenko; Vlad Shakhuro; Anna Vorontsova; Anton Konushin; Anton Antonov; Alexander Krapukhin; Denis Shepelev; Konstantin Soshin
Linearizing Models for Efficient yet Robust Private Inference. (68%)Sreetama Sarkar; Souvik Kundu; Peter A. Beerel
A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs. (26%)Kasimir Tanner; Matteo Vilucchio; Bruno Loureiro; Florent Krzakala
Is Adversarial Training with Compressed Datasets Effective? (10%)Tong Chen; Raghavendra Selvan
Reinforcement Learning as a Catalyst for Robust and Fair Federated Learning: Deciphering the Dynamics of Client Contributions. (9%)Jialuo He; Wei Chen; Xiaojin Zhang
2024-02-07
Adversarial Robustness Through Artifact Design. (99%)Tsufit Shua; Liron David; Mahmood Sharif
Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models! (98%)Shashank Kotyan; Po-Yuan Mao; Pin-Yu Chen; Danilo Vasconcellos Vargas
Analyzing Adversarial Inputs in Deep Reinforcement Learning. (96%)Davide Corsi; Guy Amir; Guy Katz; Alessandro Farinelli
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. (1%)Boyi Wei; Kaixuan Huang; Yangsibo Huang; Tinghao Xie; Xiangyu Qi; Mengzhou Xia; Prateek Mittal; Mengdi Wang; Peter Henderson
2024-02-06
Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping. (98%)Qinliang Lin; Cheng Luo; Zenghao Niu; Xilin He; Weicheng Xie; Yuanbo Hou; Linlin Shen; Siyang Song
Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning. (98%)Sarwar Khan
SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems. (76%)Oubo Ma; Yuwen Pu; Linkang Du; Yang Dai; Ruo Wang; Xiaolei Liu; Yingcai Wu; Shouling Ji
PAC-Bayesian Adversarially Robust Generalization Bounds for Graph Neural Network. (75%)Tan Sun; Junhong Lin
Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons. (74%)Zhenyu Liu; Garrett Gagnon; Swagath Venkataramani; Liu Liu
BotSSCL: Social Bot Detection with Self-Supervised Contrastive Learning. (64%)Mohammad Majid Akhtar; Navid Shadman Bhuiyan; Rahat Masood; Muhammad Ikram; Salil S. Kanhere
Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses. (26%)Hao Fang; Yixiang Qiu; Hongyao Yu; Wenbo Yu; Jiawei Kong; Baoli Chong; Bin Chen; Xuan Wang; Shu-Tao Xia; Ke Xu
Studying Vulnerable Code Entities in R. (10%)Zixiao Zhao; Millon Madhur Das; Fatemeh H. Fard
DeMarking: A Defense for Network Flow Watermarking in Real-Time. (10%)Yali Yuan; Jian Ge; Guang Cheng
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal. (2%)Mantas Mazeika; Long Phan; Xuwang Yin; Andy Zou; Zifan Wang; Norman Mu; Elham Sakhaee; Nathaniel Li; Steven Basart; Bo Li; David Forsyth; Dan Hendrycks
2024-02-05
A Generative Approach to Surrogate-based Black-box Attacks. (99%)Raha Moraffah; Huan Liu
Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics. (99%)Shuai Li; Xiaoyu Jiang; Xiaoguang Ma
Arabic Synonym BERT-based Adversarial Examples for Text Classification. (99%)Norah Alshahrani; Saied Alshahrani; Esma Wali; Jeanna Matthews
Generalization Properties of Adversarial Training for $\ell_0$-Bounded Adversarial Attacks. (92%)Payam Delgosha; Hamed Hassani; Ramtin Pedarsani
FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution. (89%)Qi Zhou; Dongxia Wang; Tianlin Li; Zhihong Xu; Yang Liu; Kui Ren; Wenhai Wang; Qing Guo
Time-Distributed Backdoor Attacks on Federated Spiking Learning. (83%)Gorka Abad; Stjepan Picek; Aitor Urbieta
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models. (83%)Yuancheng Xu; Jiarui Yao; Manli Shu; Yanchao Sun; Zichu Wu; Ning Yu; Tom Goldstein; Furong Huang
Partially Recentralization Softmax Loss for Vision-Language Models Robustness. (81%)Hao Wang; Xin Zhang; Jinzhe Jiang; Yaqian Zhao; Chen Li
Organic or Diffused: Can We Distinguish Human Art from AI-generated Images? (31%)Anna Yoo Jeong Ha; Josephine Passananti; Ronik Bhaskar; Shawn Shan; Reid Southen; Haitao Zheng; Ben Y. Zhao
DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models. (12%)Yang Sui; Huy Phan; Jinqi Xiao; Tianfang Zhang; Zijie Tang; Cong Shi; Yan Wang; Yingying Chen; Bo Yuan
FINEST: Stabilizing Recommendations by Rank-Preserving Fine-Tuning. (1%)Sejoon Oh; Berk Ustun; Julian McAuley; Srijan Kumar
Exploring mechanisms of Neural Robustness: probing the bridge between geometry and spectrum. (1%)Konstantin Holzhausen; Mia Merlid; Håkon Olav Torvik; Anders Malthe-Sørenssen; Mikkel Elle Lepperød
2024-02-04
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks. (99%)Ziquan Liu; Zhuo Zhi; Ilija Bogunovic; Carsten Gerner-Beuerle; Miguel Rodrigues
Adversarial Text Purification: A Large Language Model Approach for Defense. (99%)Raha Moraffah; Shubh Khandelwal; Amrita Bhattacharjee; Huan Liu
DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformers. (99%)Oryan Yehezkel; Alon Zolfi; Amit Baras; Yuval Elovici; Asaf Shabtai
Exploiting Class Probabilities for Black-box Sentence-level Attacks. (75%)Raha Moraffah; Huan Liu
Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approach. (41%)Brian Etter; James Lee Hu; Mohammedreza Ebrahimi; Weifeng Li; Xin Li; Hsinchun Chen
Adversarial Data Augmentation for Robust Speaker Verification. (1%)Zhenyu Zhou; Junhui Chen; Namin Wang; Lantian Li; Dong Wang
2024-02-03
Seeing is not always believing: The Space of Harmless Perturbations. (99%)Lu Chen; Shaofeng Li; Benhao Huang; Fan Yang; Zheng Li; Jie Li; Yuan Luo
Evaluating the Robustness of Off-Road Autonomous Driving Segmentation against Adversarial Attacks: A Dataset-Centric analysis. (96%)Pankaj Deoli; Rohit Kumar; Axel Vierling; Karsten Berns
Your Diffusion Model is Secretly a Certifiably Robust Classifier. (91%)Huanran Chen; Yinpeng Dong; Shitong Shao; Zhongkai Hao; Xiao Yang; Hang Su; Jun Zhu
MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers. (76%)Yatong Bai; Mo Zhou; Vishal M. Patel; Somayeh Sojoudi
Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Models. (68%)Alapan Kuila; Somnath Jena; Sudeshna Sarkar; Partha Pratim Chakrabarti
Universal Post-Training Reverse-Engineering Defense Against Backdoors in Deep Neural Networks. (31%)Xi Li; Hang Wang; David J. Miller; George Kesidis
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error. (10%)Haoran Li; Zicheng Zhang; Wang Luo; Congying Han; Yudong Hu; Tiande Guo; Shichen Liao
Invisible Finger: Practical Electromagnetic Interference Attack on Touchscreen-based Electronic Devices. (9%)Haoqi Shan; Boyi Zhang; Zihao Zhan; Dean Sullivan; Shuo Wang; Yier Jin
Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models. (5%)Yongshuo Zong; Ondrej Bohdal; Tingyang Yu; Yongxin Yang; Timothy Hospedales
Data Poisoning for In-context Learning. (5%)Pengfei He; Han Xu; Yue Xing; Hui Liu; Makoto Yamada; Jiliang Tang
2024-02-02
HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text. (99%)Han Liu; Zhi Xu; Xiaotong Zhang; Feng Zhang; Fenglong Ma; Hongyang Chen; Hong Yu; Xianchao Zhang
$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples. (99%)Antonio Emanuele Cinà; Francesco Villani; Maura Pintor; Lea Schönherr; Battista Biggio; Marcello Pelillo
STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition. (99%)Yi Chang; Zhao Ren; Zixing Zhang; Xin Jing; Kun Qian; Xi Shao; Bin Hu; Tanja Schultz; Björn W. Schuller
Delving into Decision-based Black-box Attacks on Semantic Segmentation. (93%)Zhaoyu Chen; Zhengyang Shan; Jingwen Chang; Kaixun Jiang; Dingkang Yang; Yiting Cheng; Wenqiang Zhang
SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding. (92%)Chanho Park; Namyoon Lee
Unlearnable Examples For Time Series. (86%)Yujing Jiang; Xingjun Ma; Sarah Monazam Erfani; James Bailey
Preference Poisoning Attacks on Reward Model Learning. (83%)Junlin Wu; Jiongxiao Wang; Chaowei Xiao; Chenguang Wang; Ning Zhang; Yevgeniy Vorobeychik
Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting. (3%)Yi Dong; Yingjie Wang; Mariana Gama; Mustafa A. Mustafa; Geert Deconinck; Xiaowei Huang
S2malloc: Statistically Secure Allocator for Use-After-Free Protection And More. (3%)Ruizhe Wang; Meng Xu; N. Asokan
Cheating Suffix: Targeted Attack to Text-To-Image Diffusion Models with Multi-Modal Priors. (2%)Dingcheng Yang; Yang Bai; Xiaojun Jia; Yang Liu; Xiaochun Cao; Wenjian Yu
Fundamental Challenges in Cybersecurity and a Philosophy of Vulnerability-Guided Hardening. (1%)Marcel Böhme
What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement. (1%)Xisen Jin; Xiang Ren
2024-02-01
Benchmarking Transferable Adversarial Attacks. (98%)Zhibo Jin; Jiayu Zhang; Zhiyu Zhu; Huaming Chen
Hidding the Ghostwriters: An Adversarial Evaluation of AI-Generated Student Essay Detection. (70%)Xinlin Peng; Ying Zhou; Ben He; Le Sun; Yingfei Sun
Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization. (64%)Arezoo Rajabi; Reeya Pimple; Aiswarya Janardhanan; Surudhi Asokraj; Bhaskar Ramasubramanian; Radha Poovendran
Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks. (45%)Maan Qraitem; Nazia Tasnim; Piotr Teterwak; Kate Saenko; Bryan A. Plummer
Approximating Optimal Morphing Attacks using Template Inversion. (9%)Laurent Colbois; Hatef Otroshi Shahreza; Sébastien Marcel
Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance. (8%)Wenqi Wei; Ling Liu
Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack. (1%)Tiansheng Huang; Sihao Hu; Ling Liu
algoXSSF: Detection and analysis of cross-site request forgery (XSRF) and cross-site scripting (XSS) attacks via Machine learning algorithms. (1%)Naresh Kshetri; Dilip Kumar; James Hutson; Navneet Kaur; Omar Faruq Osama
2024-01-31
Adversarial Quantum Machine Learning: An Information-Theoretic Generalization Analysis. (95%)Petros Georgiou; Sharu Theresa Jose; Osvaldo Simeone
Invariance-powered Trustworthy Defense via Remove Then Restore. (70%)Xiaowei Fu; Yuhang Zhou; Lina Ma; Lei Zhang
BrainLeaks: On the Privacy-Preserving Properties of Neuromorphic Architectures against Model Inversion Attacks. (13%)Hamed Poursiami; Ihsen Alouani; Maryam Parsa
LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks. (9%)Kaike Zhang; Qi Cao; Yunfan Wu; Fei Sun; Huawei Shen; Xueqi Cheng
Logit Poisoning Attack in Distillation-based Federated Learning and its Countermeasures. (4%)Yonghao Yu; Shunan Zhu; Jinglu Hu
Manipulating Predictions over Discrete Inputs in Machine Teaching. (1%)Xiaodong Wu; Yufei Han; Hayssam Dahrouj; Jianbing Ni; Zhenwen Liang; Xiangliang Zhang
Ambush from All Sides: Understanding Security Threats in Open-Source Software CI/CD Pipelines. (1%)Ziyue Pan; Wenbo Shen; Xingkai Wang; Yutian Yang; Rui Chang; Yao Liu; Chengwei Liu; Yang Liu; Kui Ren
2024-01-30
Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers. (99%)Lei Xu; Sarah Alnegheimish; Laure Berti-Equille; Alfredo Cuesta-Infante; Kalyan Veeramachaneni
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks. (98%)Andy Zhou; Bo Li; Haohan Wang
Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR. (98%)Bowen Peng; Bo Peng; Jingyuan Xia; Tianpeng Liu; Yongxiang Liu; Li Liu
AdvGPS: Adversarial GPS for Multi-Agent Perception Attack. (95%)Jinlong Li; Baolu Li; Xinyu Liu; Jianwu Fang; Felix Juefei-Xu; Qing Guo; Hongkai Yu
Game-Theoretic Unlearnable Example Generator. (92%)Shuang Liu; Yihan Wang; Xiao-Shan Gao
Camouflage Adversarial Attacks on Multiple Agent Systems. (87%)Ziqing Lu; Guanlin Liu; Lifeng Lai; Weiyu Xu
Weak-to-Strong Jailbreaking on Large Language Models. (76%)Xuandong Zhao; Xianjun Yang; Tianyu Pang; Chao Du; Lei Li; Yu-Xiang Wang; William Yang Wang
A Proactive and Dual Prevention Mechanism against Illegal Song Covers empowered by Singing Voice Conversion. (75%)Guangke Chen; Yedi Zhang; Fu Song; Ting Wang; Xiaoning Du; Yang Liu
Improving QA Model Performance with Cartographic Inoculation. (26%)Allen UT Austin Chen; Okan UT Austin Tanrikulu
Towards Visual Syntactical Understanding. (4%)Sayeed Shafayet Chowdhury; Soumyadeep Chandra; Kaushik Roy
Provably Robust Multi-bit Watermarking for AI-generated Text via Error Correction Code. (2%)Wenjie Qu; Dong Yin; Zixin He; Wei Zou; Tianyang Tao; Jinyuan Jia; Jiaheng Zhang
2024-01-29
LESSON: Multi-Label Adversarial False Data Injection Attack for Deep Learning Locational Detection. (99%)Jiwei Tian; Chao Shen; Buhong Wang; Xiaofang Xia; Meng Zhang; Chenhao Lin; Qian Li
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization. (92%)Guang Lin; Chao Li; Jianhai Zhang; Toshihisa Tanaka; Qibin Zhao
Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks. (68%)Lulu Xue; Shengshan Hu; Ruizhi Zhao; Leo Yu Zhang; Shengqing Hu; Lichao Sun; Dezhong Yao
GPS: Graph Contrastive Learning via Multi-scale Augmented Views from Adversarial Pooling. (5%)Wei Ju; Yiyang Gu; Zhengyang Mao; Ziyue Qiao; Yifang Qin; Xiao Luo; Hui Xiong; Ming Zhang
Security and Privacy Challenges of Large Language Models: A Survey. (1%)Badhan Chandra Das; M. Hadi Amini; Yanzhao Wu
2024-01-28
Addressing Noise and Efficiency Issues in Graph-Based Machine Learning Models From the Perspective of Adversarial Attack. (83%)Yongyu Wang
Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perception. (75%)Forrest McKee; David Noever
Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability. (26%)Hao Wang; Shangwei Guo; Jialing He; Hangcheng Liu; Tianwei Zhang; Tao Xiang
2024-01-27
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks. (98%)Ping Guo; Fei Liu; Xi Lin; Qingchuan Zhao; Qingfu Zhang
2024-01-26
Set-Based Training for Neural Network Verification. (99%)Lukas Koller; Tobias Ladner; Matthias Althoff
Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement. (91%)Nuoyan Zhou; Dawei Zhou; Decheng Liu; Xinbo Gao; Nannan Wang
Multi-Trigger Backdoor Attacks: More Triggers, More Threats. (82%)Yige Li; Xingjun Ma; Jiabo He; Hanxun Huang; Yu-Gang Jiang
Adversarial Attacks and Defenses in 6G Network-Assisted IoT Systems. (81%)Bui Duc Son; Nguyen Tien Hoa; Chien Trinh Van; Waqas Khalid; Mohamed Amine Ferrag; Wan Choi; Merouane Debbah
Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training. (62%)Shruthi Gowda; Bahram Zonooz; Elahe Arani
Asymptotic Behavior of Adversarial Training Estimator under $\ell_\infty$-Perturbation. (22%)Yiling Xie; Xiaoming Huo
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective. (22%)Yue Xing; Xiaofeng Lin; Qifan Song; Yi Xu; Belinda Zeng; Guang Cheng
MEA-Defender: A Robust Watermark against Model Extraction Attack. (13%)Peizhuo Lv; Hualong Ma; Kai Chen; Jiachen Zhou; Shengzhi Zhang; Ruigang Liang; Shenchen Zhu; Pan Li; Yingjun Zhang
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning. (2%)Baoyuan Wu; Hongrui Chen; Mingda Zhang; Zihao Zhu; Shaokui Wei; Danni Yuan; Mingli Zhu; Ruotong Wang; Li Liu; Chao Shen
2024-01-25
Sparse and Transferable Universal Singular Vectors Attack. (99%)Kseniia Kuvshinova; Olga Tsymboi; Ivan Oseledets
Friendly Attacks to Improve Channel Coding Reliability. (54%)Anastasiia Kurmukova; Deniz Gunduz
Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models. (16%)Erik Arakelyan; Zhaoqi Liu; Isabelle Augenstein
The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness. (2%)Mengyao Du; Miao Zhang; Yuwen Pu; Kai Xu; Shouling Ji; Quanjun Yin
Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations. (1%)Patricia Pauli; Aaron Havens; Alexandre Araujo; Siddharth Garg; Farshad Khorrami; Frank Allgöwer; Bin Hu
Physical Trajectory Inference Attack and Defense in Decentralized POI Recommendation. (1%)Jing Long; Tong Chen; Guanhua Ye; Kai Zheng; Nguyen Quoc Viet Hung; Hongzhi Yin
2024-01-24
A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE). (92%)Charles Meyers; Mohammad Reza Saleh Sedghpour; Tommy Löfstedt; Erik Elmroth
Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint. (86%)Zhongjie Shi; Fanghui Liu; Yuan Cao; Johan A. K. Suykens
WPDA: Frequency-based Backdoor Attack with Wavelet Packet Decomposition. (76%)Zhengyao Song; Yongqiang Li; Danni Yuan; Li Liu; Shaokui Wei; Baoyuan Wu
Exploring Adversarial Threat Models in Cyber Physical Battery Systems. (76%)Shanthan Kumar Padisala; Shashank Dhananjay Vyas; Satadru Dey
Fluent dreaming for language models. (64%)T. Ben Confirm Labs Thompson; Zygimantas Confirm Labs Straznickas; Michael Confirm Labs Sklar
2024-01-23
Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size. (99%)Junlin Liu; Xinchen Lyu
Securing Recommender System via Cooperative Training. (80%)Qingyang Wang; Chenwang Wu; Defu Lian; Enhong Chen
Compositional Generative Inverse Design. (56%)Tailin Wu; Takashi Maruyama; Long Wei; Tao Zhang; Yilun Du; Gianluca Iaccarino; Jure Leskovec
AdCorDA: Classifier Refinement via Adversarial Correction and Domain Adaptation. (33%)Lulan Shen; Ali Edalati; Brett Meyer; Warren Gross; James J. Clark
ToDA: Target-oriented Diffusion Attacker against Recommendation System. (13%)Xiaohao Liu; Zhulin Tao; Ting Jiang; He Chang; Yunshan Ma; Xianglin Huang; Xiang Wang
DAFA: Distance-Aware Fair Adversarial Training. (2%)Hyungyu Lee; Saehyung Lee; Hyemi Jang; Junsung Park; Ho Bae; Sungroh Yoon
The twin peaks of learning neural networks. (2%)Elizaveta Demyanenko; Christoph Feinauer; Enrico M. Malatesta; Luca Saglietti
2024-01-22
Fast Adversarial Training against Textual Adversarial Attacks. (99%)Yichen Yang; Xin Liu; Kun He
A Training-Free Defense Framework for Robust Learned Image Compression. (74%)Myungseo Song; Jinyoung Choi; Bohyung Han
Adversarial speech for voice privacy protection from Personalized Speech generation. (73%)Shihao Chen; Liping Chen; Jie Zhang; KongAik Lee; Zhenhua Ling; Lirong Dai
NEUROSEC: FPGA-Based Neuromorphic Audio Security. (13%)Murat Isik; Hiruna Vishwamith; Yusuf Sur; Kayode Inadagbo; I. Can Dikmen
Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them. (13%)Chao Liu; Boxi Chen; Wei Shao; Chris Zhang; Kelvin Wong; Yi Zhang
Robustness to distribution shifts of compressed networks for edge devices. (8%)Lulan Shen; Ali Edalati; Brett Meyer; Warren Gross; James J. Clark
Text Embedding Inversion Security for Multilingual Language Models. (2%)Yiyi Chen; Heather Lent; Johannes Bjerva
Out-of-Distribution Detection & Applications With Ablated Learned Temperature Energy. (1%)Will LeVine; Benjamin Pikus; Jacob Phillips; Berk Norman; Fernando Amat Gil; Sean Hendryx
2024-01-21
How Robust Are Energy-Based Models Trained With Equilibrium Propagation? (99%)Siddharth Mansingh; Michal Kucer; Garrett Kenyon; Juston Moore; Michael Teti
Analyzing the Quality Attributes of AI Vision Models in Open Repositories Under Adversarial Attacks. (56%)Zerui Wang; Yan Liu
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts. (11%)Kiyoon Kim; Shreyank N Gowda; Panagiotis Eustratiadis; Antreas Antoniou; Robert B Fisher
Efficient local linearity regularization to overcome catastrophic overfitting. (8%)Elias Abad Rocamora; Fanghui Liu; Grigorios G. Chrysos; Pablo M. Olmos; Volkan Cevher
2024-01-20
Susceptibility of Adversarial Attack on Medical Image Segmentation Models. (99%)Zhongxuan Wang; Leo Xu
Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion. (96%)Aly M. Kassem; Sherif Saad
CARE: Ensemble Adversarial Robustness Evaluation Against Adaptive Attackers for Security Applications. (80%)Hangsheng Zhang; Jiqiang Liu; Jinsong Dong
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images. (33%)Kuofeng Gao; Yang Bai; Jindong Gu; Shu-Tao Xia; Philip Torr; Zhifeng Li; Wei Liu
2024-01-19
PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks. (99%)Ping Guo; Zhiyuan Yang; Xi Lin; Qingchuan Zhao; Qingfu Zhang
Explainable and Transferable Adversarial Attack for ML-Based Network Intrusion Detectors. (99%)Hangsheng Zhang; Dongqi Han; Yinlong Liu; Zhiliang Wang; Jiyan Sun; Shangyuan Zhuang; Jiqiang Liu; Jinsong Dong
The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness. (98%)Yifan Hao; Tong Zhang
FIMBA: Evaluating the Robustness of AI in Genomics via Feature Importance Adversarial Attacks. (56%)Heorhii Skovorodnikov; Hoda Alkhzaimi
Adversarially Robust Signed Graph Contrastive Learning from Balance Augmentation. (10%)Jialong Zhou; Xing Ai; Yuni Lai; Kai Zhou
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models. (3%)Zhen Xiang; Fengqing Jiang; Zidi Xiong; Bhaskar Ramasubramanian; Radha Poovendran; Bo Li
Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually. (1%)Mazal Bethany; Brandon Wherry; Nishant Vishwamitra; Peyman Najafirad
2024-01-18
HGAttack: Transferable Heterogeneous Graph Adversarial Attack. (99%)He Zhao; Zhiwei Zeng; Yongwei Wang; Deheng Ye; Chunyan Miao
Hijacking Attacks against Neural Networks by Analyzing Training Data. (99%)Yunjie Ge; Qian Wang; Huayang Huang; Qi Li; Cong Wang; Chao Shen; Lingchen Zhao; Peipei Jiang; Zheng Fang; Shenyi Zhang
Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers. (99%)Tuc Nguyen; Thai Le
Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security. (92%)Marsalis Gibson; David Babazadeh; Claire Tomlin; Shankar Sastry
Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation. (80%)Janvi Thakkar; Giulio Zizzo; Sergio Maffeis
Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognition. (15%)Yu Yu; Chao-Han Huck Yang; Tuan Dinh; Sungho Ryu; Jari Kolehmainen; Roger Ren; Denis Filimonov; Prashanth G. Shivakumar; Ankur Gandhe; Ariya Rastow; Jia Xu; Ivan Bulyko; Andreas Stolcke
Power in Numbers: Robust reading comprehension by finetuning with four adversarial sentences per example. (13%)Ariel Marcus
Cross-Modality Perturbation Synergy Attack for Person Re-identification. (3%)Yunpeng Gong; Zhun Zhong; Yansong Qu; Zhiming Luo; Rongrong Ji; Min Jiang
Vulnerabilities of Foundation Model Integrated Federated Learning Under Adversarial Threats. (2%)Chen Wu; Xi Li; Jiaqi Wang
Large Language Models are Efficient Learners of Noise-Robust Speech Recognition. (1%)Yuchen Hu; Chen Chen; Chao-Han Huck Yang; Ruizhe Li; Chao Zhang; Pin-Yu Chen; EnSiong Chng
2024-01-17
Towards Scalable and Robust Model Versioning. (93%)Wenxin Ding; Arjun Nitin Bhagoji; Ben Y. Zhao; Haitao Zheng
Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack. (93%)Zhongliang Guo; Junhao Dong; Yifei Qian; Kaixuan Wang; Weiye Li; Ziheng Guo; Yuheng Wang; Yanli Li; Ognjen Arandjelović; Lei Fang
MITS-GAN: Safeguarding Medical Imaging from Tampering with Generative Adversarial Networks. (26%)Giovanni Pasqualino; Luca Guarnera; Alessandro Ortis; Sebastiano Battiato
A GAN-based data poisoning framework against anomaly detection in vertical federated learning. (3%)Xiaolin Chen; Daoguang Zan; Wei Li; Bei Guan; Yongji Wang
An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification. (3%)Nicolas Garcia Trillos; Matt Jacobs; Jakwang Kim; Matthew Werenski
Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initialization. (1%)Yoonhwa Jung; Ikhyun Cho; Shun-Hsiang Hsu; Julia Hockenmaier
Caught in the Quicksand of Reasoning, Far from AGI Summit: Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions. (1%)Pengfei Hong; Deepanway Ghosal; Navonil Majumder; Somak Aditya; Rada Mihalcea; Soujanya Poria
2024-01-16
Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks. (99%)Chenyu Zhang; Lanjun Wang; Anan Liu
Bag of Tricks to Boost Adversarial Transferability. (99%)Zeliang Zhang; Rongyi Zhu; Wei Yao; Xiaosen Wang; Chenliang Xu
A Generative Adversarial Attack for Multilingual Text Classifiers. (99%)Tom Roth; Inigo Jauregi Unanue; Alsharif Abuadbba; Massimo Piccardi
PPR: Enhancing Dodging Attacks while Maintaining Impersonation Attacks on Face Recognition Systems. (99%)Fengfan Zhou; Heifei Ling
Robust Localization of Key Fob Using Channel Impulse Response of Ultra Wide Band Sensors for Keyless Entry Systems. (92%)Abhiram Kolli; Filippo Casamassima; Horst Possegger; Horst Bischof
The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images. (87%)Nicholas Konz; Maciej A. Mazurowski
RandOhm: Mitigating Impedance Side-channel Attacks using Randomized Circuit Configurations. (9%)Saleh Khalaj Monfared; Domenic Forte; Shahin Tajik
Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning. (8%)Yu Jiang; Jiyuan Shen; Ziyao Liu; Chee Wei Tan; Kwok-Yan Lam
IPR-NeRF: Ownership Verification meets Neural Radiance Field. (3%)Win Kent Ong; Kam Woh Ng; Chee Seng Chan; Yi Zhe Song; Tao Xiang
IoTWarden: A Deep Reinforcement Learning Based Real-time Defense System to Mitigate Trigger-action IoT Attacks. (1%)Md Morshed Department of Software and Information Systems, University of North Carolina at Charlotte, Charlotte, USA Alam; Israt Department of Computer Science, University of Memphis, Memphis, USA Jahan; Weichao Department of Software and Information Systems, University of North Carolina at Charlotte, Charlotte, USA Wang
2024-01-15
Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes. (99%)Shayan Mohajer Hamidi; Linfeng Ye
Authorship Obfuscation in Multilingual Machine-Generated Text Detection. (13%)Dominik Macko; Robert Moro; Adaku Uchendu; Ivan Srba; Jason Samuel Lucas; Michiharu Yamashita; Nafis Irtiza Tripto; Dongwon Lee; Jakub Simko; Maria Bielikova
2024-01-14
LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts. (80%)Shoupeng Ren; Lipeng He; Tianyu Tu; Di Wu; Jian Liu; Kui Ren; Chun Chen
Crafter: Facial Feature Crafting against Inversion-based Identity Theft on Deep Models. (70%)Shiming Wang; Zhe Ji; Liyao Xiang; Hao Zhang; Xinbing Wang; Chenghu Zhou; Bo Li
2024-01-13
Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability. (99%)Junxi Chen; Junhao Dong; Xiaohua Xie
Left-right Discrepancy for Adversarial Attack on Stereo Networks. (98%)Pengfei Wang; Xiaofei Hui; Beijia Lu; Nimrod Lilith; Jun Liu; Sameer Alam
2024-01-12
Adversarial Examples are Misaligned in Diffusion Model Manifolds. (98%)Peter Lorenz; Ricard Durall; Janis Keuper
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs. (2%)Yi Zeng; Hongpeng Lin; Jingwen Zhang; Diyi Yang; Ruoxi Jia; Weiyan Shi
Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning. (1%)Chenyang Wang; Junjun Jiang; Xingyu Hu; Xianming Liu; Xiangyang Ji
An Analytical Framework for Modeling and Synthesizing Malicious Attacks on ACC Vehicles. (1%)Shian Wang
Intention Analysis Makes LLMs A Good Jailbreak Defender. (1%)Yuqi Zhang; Liang Ding; Lefei Zhang; Dacheng Tao
2024-01-11
GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model. (99%)Zhiyu Zhu; Huaming Chen; Xinyi Wang; Jiayu Zhang; Zhibo Jin; Kim-Kwang Raymond Choo; Jun Shen; Dong Yuan
Universal Vulnerabilities in Large Language Models: In-context Learning Backdoor Attacks. (61%)Shuai Zhao; Meihuizi Jia; Luu Anh Tuan; Jinming Wen
Open the Pandora's Box of LLMs: Jailbreaking LLMs through Representation Engineering. (22%)Tianlong Li; Shihan Dou; Wenhao Liu; Muling Wu; Changze Lv; Xiaoqing Zheng; Xuanjing Huang
Can We Trust the Unlabeled Target Data? Towards Backdoor Attack and Defense on Model Adaptation. (8%)Lijun Sheng; Jian Liang; Ran He; Zilei Wang; Tieniu Tan
Manipulating Feature Visualizations with Gradient Slingshots. (3%)Dilyara Bareeva; Marina M. -C. Höhne; Alexander Warnecke; Lukas Pirch; Klaus-Robert Müller; Konrad Rieck; Kirill Bykov
Combating Adversarial Attacks with Multi-Agent Debate. (3%)Steffi Chern; Zhen Fan; Andy Liu
2024-01-10
Exploring Vulnerabilities of No-Reference Image Quality Assessment Models: A Query-Based Black-Box Method. (83%)Chenxi Yang; Yujia Liu; Dingquan Li; Tingting Jiang
TrustLLM: Trustworthiness in Large Language Models. (75%)Lichao Sun; Yue Huang; Haoran Wang; Siyuan Wu; Qihui Zhang; Chujie Gao; Yixin Huang; Wenhan Lyu; Yixuan Zhang; Xiner Li; Zhengliang Liu; Yixin Liu; Yijue Wang; Zhikun Zhang; Bhavya Kailkhura; Caiming Xiong; Chaowei Xiao; Chunyuan Li; Eric Xing; Furong Huang; Hao Liu; Heng Ji; Hongyi Wang; Huan Zhang; Huaxiu Yao; Manolis Kellis; Marinka Zitnik; Meng Jiang; Mohit Bansal; James Zou; Jian Pei; Jian Liu; Jianfeng Gao; Jiawei Han; Jieyu Zhao; Jiliang Tang; Jindong Wang; John Mitchell; Kai Shu; Kaidi Xu; Kai-Wei Chang; Lifang He; Lifu Huang; Michael Backes; Neil Zhenqiang Gong; Philip S. Yu; Pin-Yu Chen; Quanquan Gu; Ran Xu; Rex Ying; Shuiwang Ji; Suman Jana; Tianlong Chen; Tianming Liu; Tianyi Zhou; Willian Wang; Xiang Li; Xiangliang Zhang; Xiao Wang; Xing Xie; Xun Chen; Xuyu Wang; Yan Liu; Yanfang Ye; Yinzhi Cao; Yong Chen; Yue Zhao
SENet: Visual Detection of Online Social Engineering Attack Campaigns. (4%)Irfan Ozen; Karthika Subramani; Phani Vadrevu; Roberto Perdisci
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training. (2%)Evan Hubinger; Carson Denison; Jesse Mu; Mike Lambert; Meg Tong; Monte MacDiarmid; Tamera Lanham; Daniel M. Ziegler; Tim Maxwell; Newton Cheng; Adam Jermyn; Amanda Askell; Ansh Radhakrishnan; Cem Anil; David Duvenaud; Deep Ganguli; Fazl Barez; Jack Clark; Kamal Ndousse; Kshitij Sachan; Michael Sellitto; Mrinank Sharma; Nova DasSarma; Roger Grosse; Shauna Kravec; Yuntao Bai; Zachary Witten; Marina Favaro; Jan Brauner; Holden Karnofsky; Paul Christiano; Samuel R. Bowman; Logan Graham; Jared Kaplan; Sören Mindermann; Ryan Greenblatt; Buck Shlegeris; Nicholas Schiefer; Ethan Perez
CoLafier: Collaborative Noisy Label Purifier With Local Intrinsic Dimensionality Guidance. (1%)Dongyu Zhang; Ruofan Hu; Elke Rundensteiner
Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning. (1%)Zhangchen Xu; Fengqing Jiang; Luyao Niu; Jinyuan Jia; Radha Poovendran
FBSDetector: Fake Base Station and Multi Step Attack Detection in Cellular Networks using Machine Learning. (1%)Kazi Samin Mubasshir; Imtiaz Karim; Elisa Bertino
2024-01-09
Revisiting Adversarial Training at Scale. (26%)Zeyu Wang; Xianhang Li; Hongru Zhu; Cihang Xie
SoK: Facial Deepfake Detectors. (11%)Binh M. Le; Jiwon Kim; Shahroz Tariq; Kristen Moore; Alsharif Abuadbba; Simon S. Woo
Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks. (3%)Tanmay Garg; Deepika Vemuri; Vineeth N Balasubramanian
2024-01-08
Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness. (99%)Sibo Wang; Jie Zhang; Zheng Yuan; Shiguang Shan
Robustness Assessment of a Runway Object Classifier for Safe Aircraft Taxiing. (54%)Yizhak Elboher; Raya Elsaleh; Omri Isac; Mélanie Ducoffe; Audrey Galametz; Guillaume Povéda; Ryma Boumazouza; Noémie Cohen; Guy Katz
Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study. (45%)Qiyu Kang; Kai Zhao; Yang Song; Yihang Xie; Yanan Zhao; Sijie Wang; Rui She; Wee Peng Tay
Logits Poisoning Attack in Federated Distillation. (12%)Yuhan Tang; Zhiyuan Wu; Bo Gao; Tian Wen; Yuwei Wang; Sheng Sun
Attack-Resilient Image Watermarking Using Stable Diffusion. (3%)Lijun Zhang; Xiao Liu; Antoni Viros Martin; Cindy Xiong Bearfield; Yuriy Brun; Hui Guan
Dense Hopfield Networks in the Teacher-Student Setting. (1%)Robin Thériault; Daniele Tantari
2024-01-07
Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perception. (87%)Takami Sato; Sri Hrushikesh Varma Bhupathiraju; Michael Clifford; Takeshi Sugawara; Qi Alfred Chen; Sara Rampazzi
Data-Driven Subsampling in the Presence of an Adversarial Actor. (86%)Abu Shafin Mohammad Mahdee Jameel; Ahmed P. Mohamed; Jinho Yi; Aly El Gamal; Akshay Malhotra
ROIC-DM: Robust Text Inference and Classification via Diffusion Model. (33%)Shilong Yuan; Wei Yuan; Hongzhi Yin; Tieke He
2024-01-06
Data-Dependent Stability Analysis of Adversarial Training. (98%)Yihan Wang; Shuang Liu; Xiao-Shan Gao
End-to-End Anti-Backdoor Learning on Images and Time Series. (61%)Yujing Jiang; Xingjun Ma; Sarah Monazam Erfani; Yige Li; James Bailey
2024-01-05
Transferable Learned Image Compression-Resistant Adversarial Perturbations. (99%)Yang Sui; Zhuohang Li; Ding Ding; Xiang Pan; Xiaozhong Xu; Shan Liu; Zhenzhong Chen
Enhancing targeted transferability via feature space fine-tuning. (98%)Hui Zeng; Biwei Chen; Anjie Peng
Calibration Attack: A Framework For Adversarial Attacks Targeting Calibration. (76%)Stephen Obadinma; Xiaodan Zhu; Hongyu Guo
A backdoor attack against link prediction tasks with graph neural networks. (38%)Jiazhu Dai; Haoyu Sun
TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks. (1%)Khondoker Murad Hossain; Tim Oates
MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance. (1%)Renjie Pi; Tianyang Han; Yueqi Xie; Rui Pan; Qing Lian; Hanze Dong; Jipeng Zhang; Tong Zhang
2024-01-04
Vulnerabilities Unveiled: Adversarially Attacking a Multimodal Vision Langauge Model for Pathology Imaging. (99%)Jai Prakash Veerla; Poojitha Thota; Partha Sai Guttikonda; Shirin Nilizadeh; Jacob M. Luber
A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples. (99%)Ryota Iijima; Sayaka Shiota; Hitoshi Kiya
AdvSQLi: Generating Adversarial SQL Injections against Real-world WAF-as-a-service. (95%)Zhenqing Qu; Xiang Ling; Ting Wang; Xiang Chen; Shouling Ji; Chunming Wu
Evasive Hardware Trojan through Adversarial Power Trace. (92%)Behnam Omidi; Khaled N. Khasawneh; Ihsen Alouani
Object-oriented backdoor attack against image captioning. (76%)Meiling Li; Nan Zhong; Xinpeng Zhang; Zhenxing Qian; Sheng Li
DEM: A Method for Certifying Deep Neural Network Classifier Outputs in Aerospace. (2%)Guy Katz; Natan Levy; Idan Refaeli; Raz Yerushalmi
Secure Control of Connected and Automated Vehicles Using Trust-Aware Robust Event-Triggered Control Barrier Functions. (2%)H M Sabbir Ahmad; Ehsan Sabouni; Akua Dickson; Wei Xiao; Christos G. Cassandras; Wenchao Li
A Survey Analyzing Generalization in Deep Reinforcement Learning. (1%)Ezgi Korkmaz
2024-01-03
Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement. (92%)Zheng Yuan; Jie Zhang; Yude Wang; Shiguang Shan; Xilin Chen
Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack. (62%)Ruofei Wang; Renjie Wan; Zongyu Guo; Qing Guo; Rui Huang
FullLoRA-AT: Efficiently Boosting the Robustness of Pretrained Vision Transformers. (33%)Zheng Yuan; Jie Zhang; Shiguang Shan
Integrated Cyber-Physical Resiliency for Power Grids under IoT-Enabled Dynamic Botnet Attacks. (22%)Yuhan Zhao; Juntao Chen; Quanyan Zhu
Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation. (1%)Xuannan Liu; Yaoyao Zhong; Weihong Deng; Hongzhi Shi; Xingchen Cui; Yunfeng Yin; Dongchao Wen
2024-01-02
JMA: a General Algorithm to Craft Nearly Optimal Targeted Adversarial Example. (99%)Benedetta Tondi; Wei Guo; Mauro Barni
Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing. (92%)Zhe Kong; Wentian Zhang; Tao Wang; Kaihao Zhang; Yuexiang Li; Xiaoying Tang; Wenhan Luo
SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization. (75%)Xixu Hu; Runkai Zheng; Jindong Wang; Cheuk Hang Leung; Qi Wu; Xing Xie
Unveiling the Stealthy Threat: Analyzing Slow Drift GPS Spoofing Attacks for Autonomous Vehicles in Urban Environments and Enabling the Resilience. (10%)Sagar Dasgupta; Abdullah Ahmed; Mizanur Rahman; Thejesh N. Bandi
Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control. (4%)Ka-Ho Chow; Wenqi Wei; Lei Yu
Will 6G be Semantic Communications? Opportunities and Challenges from Task Oriented and Secure Communications to Integrated Sensing. (2%)Yalin E. Sagduyu; Tugba Erpek; Aylin Yener; Sennur Ulukus
2024-01-01
Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment. (12%)Jie Zhu; Leye Wang; Xiao Han; Anmin Liu; Tao Xie
Detection and Defense Against Prominent Attacks on Preconditioned LLM-Integrated Virtual Assistants. (8%)Chun Fai Chan; Daniel Wankit Yip; Aysan Esmradi
A Novel Evaluation Framework for Assessing Resilience Against Prompt Injection Attacks in Large Language Models. (2%)Daniel Wankit Yip; Aysan Esmradi; Chun Fai Chan
2023-12-31
AR-GAN: Generative Adversarial Network-Based Defense Method Against Adversarial Attacks on the Traffic Sign Classification System of Autonomous Vehicles. (99%)M Sabbir Salek; Abdullah Al Mamun; Mashrur Chowdhury
Does Few-shot Learning Suffer from Backdoor Attacks? (98%)Xinwei Liu; Xiaojun Jia; Jindong Gu; Yuan Xun; Siyuan Liang; Xiaochun Cao
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers? (68%)Xiaoxuan Han; Songlin Yang; Wei Wang; Ziwen He; Jing Dong
2023-12-30
Explainability-Driven Leaf Disease Classification using Adversarial Training and Knowledge Distillation. (84%)Sebastian-Vasile Echim; Iulian-Marius Tăiatu; Dumitru-Clementin Cercel; Florin Pop
CamPro: Camera-based Anti-Facial Recognition. (81%)Wenjun Zhu; Yuan Sun; Jiani Liu; Yushi Cheng; Xiaoyu Ji; Wenyuan Xu
TPatch: A Triggered Physical Adversarial Patch. (76%)Wenjun Zhu; Xiaoyu Ji; Yushi Cheng; Shibo Zhang; Wenyuan Xu
A clean-label graph backdoor attack method in node classification task. (9%)Xiaogang Xing; Ming Xu; Yujing Bai; Dongdong Yang
2023-12-29
Jatmo: Prompt Injection Defense by Task-Specific Finetuning. (54%)Julien Piet; Maha Alrashed; Chawin Sitawarin; Sizhe Chen; Zeming Wei; Elizabeth Sun; Basel Alomair; David Wagner
SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection. (11%)Qiannan Wang; Changchun Yin; Lu Zhou; Liming Fang
Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training. (9%)Dongfang Li; Baotian Hu; Qingcai Chen; Shan He
2023-12-28
Adversarial Attacks on Image Classification Models: Analysis and Defense. (99%)Jaydip Sen; Abhiraj Sen; Ananda Chatterjee
BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks. (99%)Meixi Zheng; Xuanchen Yan; Zihao Zhu; Hongrui Chen; Baoyuan Wu
Attack Tree Analysis for Adversarial Evasion Attacks. (99%)Yuki Yamaguchi; Toshiaki Aoki
Can you See me? On the Visibility of NOPs against Android Malware Detectors. (98%)Diego Soi; Davide Maiorca; Giorgio Giacinto; Harel Berger
MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World. (98%)Zheng Zhou; Hongbo Zhao; Ju Liu; Qiaosheng Zhang; Liwei Geng; Shuchang Lyu; Wenquan Feng
Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation. (92%)Dibaloke Chanda; Saba Heidari Gheshlaghi; Nasim Yahya Soltani
DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generation. (83%)Wenyi Tan; Yang Li; Chenxing Zhao; Zhunga Liu; Quan Pan
Securing NextG Systems against Poisoning Attacks on Federated Learning: A Game-Theoretic Solution. (64%)Yalin E. Sagduyu; Tugba Erpek; Yi Shi
Timeliness: A New Design Metric and a New Attack Surface. (1%)Priyanka Kaswan; Sennur Ulukus
2023-12-27
Adversarial Attacks on LoRa Device Identification and Rogue Signal Detection with Deep Learning. (98%)Yalin E. Sagduyu; Tugba Erpek
Domain Generalization with Vital Phase Augmentation. (3%)Ingyun Lee; Wooju Lee; Hyun Myung
2023-12-26
From text to multimodal: a survey of adversarial example generation in question answering systems. (92%)Gulsum Yigit; Mehmet Fatih Amasyali
Natural Adversarial Patch Generation Method Based on Latent Diffusion Model. (76%)Xianyi Chen; Fazhan Liu; Dong Jiang; Kai Yan
Robust Survival Analysis with Adversarial Regularization. (61%)Michael Potter; Stefano Maxenti; Michael Everett
Universal Pyramid Adversarial Training for Improved ViT Performance. (5%)Ping-yeh Chiang; Yipin Zhou; Omid Poursaeed; Satya Narayan Shukla; Ashish Shah; Tom Goldstein; Ser-Nam Lim
2023-12-25
GanFinger: GAN-Based Fingerprint Generation for Deep Neural Network Ownership Verification. (96%)Huali Ren; Anli Yan; Xiaojun Ren; Pei-Gen Ye; Chong-zhi Gao; Zhili Zhou; Jin Li
Adversarial Item Promotion on Visually-Aware Recommender Systems by Guided Diffusion. (84%)Lijian Chen; Wei Yuan; Tong Chen; Guanhua Ye; Quoc Viet Hung Nguyen; Hongzhi Yin
Punctuation Matters! Stealthy Backdoor Attack for Language Models. (11%)Xuan Sheng; Zhicheng Li; Zhaoyang Han; Xiangmao Chang; Piji Li
2023-12-23
Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It. (10%)Federico Siciliano; Luca Maiano; Lorenzo Papa; Federica Baccin; Irene Amerini; Fabrizio Silvestri
Pre-trained Trojan Attacks for Visual Recognition. (1%)Aishan Liu; Xinwei Zhang; Yisong Xiao; Yuguang Zhou; Siyuan Liang; Jiakai Wang; Xianglong Liu; Xiaochun Cao; Dacheng Tao
TVE: Learning Meta-attribution for Transferable Vision Explainer. (1%)Guanchu Wang; Yu-Neng Chuang; Fan Yang; Mengnan Du; Chia-Yuan Chang; Shaochen Zhong; Zirui Liu; Zhaozhuo Xu; Kaixiong Zhou; Xuanting Cai; Xia Hu
2023-12-22
MEAOD: Model Extraction Attack against Object Detectors. (83%)Zeyu Li; Chenghui Shi; Yuwen Pu; Xuhong Zhang; Yu Li; Jinbao Li; Shouling Ji
Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks. (82%)Haz Sameen Shahgir; Xianghao Kong; Greg Ver Steeg; Yue Dong
Understanding the Regularity of Self-Attention with Optimal Transport. (31%)Valérie Castin; Pierre Ablin; Gabriel Peyré
Attacking Byzantine Robust Aggregation in High Dimensions. (22%)Sarthak Choudhary; Aashish Kolluri; Prateek Saxena
SODA: Protecting Proprietary Information in On-Device Machine Learning Models. (4%)Akanksha Atrey; Ritwik Sinha; Saayan Mitra; Prashant Shenoy
Energy-based learning algorithms for analog computing: a comparative study. (2%)Benjamin Scellier; Maxence Ernoult; Jack Kendall; Suhas Kumar
Adaptive Domain Inference Attack. (1%)Yuechun Gu; Keke Chen
2023-12-21
AutoAugment Input Transformation for Highly Transferable Targeted Attacks. (99%)Haobo Lu; Xin Liu; Kun He
Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples. (98%)Ruichu Cai; Yuxuan Zhu; Jie Qiao; Zefeng Liang; Furui Liu; Zhifeng Hao
Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience. (86%)Janvi Thakkar; Giulio Zizzo; Sergio Maffeis
Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World. (74%)Chengyin Hu; Weiwen Shi
Exploiting Novel GPT-4 APIs. (8%)Kellin Pelrine; Mohammad Taufeeque; Michał Zając; Euan McLean; Adam Gleave
2023-12-20
Mutual-modality Adversarial Attack with Semantic Perturbation. (99%)Jingwen Ye; Ruonan Yu; Songhua Liu; Xinchao Wang
LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate. (99%)Tao Wu; Tie Luo; Donald C. Wunsch
Adversarial Markov Games: On Adaptive Decision-Based Attacks and Defenses. (98%)Ilias Tsingenopoulos; Vera Rimmer; Davy Preuveneers; Fabio Pierazzi; Lorenzo Cavallaro; Wouter Joosen
Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models. (98%)Jingwei Yi; Yueqi Xie; Bin Zhu; Emre Kiciman; Guangzhong Sun; Xing Xie; Fangzhao Wu
PGN: A perturbation generation network against deep reinforcement learning. (96%)Xiangjuan Li; Feifan Li; Yang Li; Quan Pan
ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks. (96%)Peng Zhao; Jiehua Zhang; Bowen Peng; Longguang Wang; YingMei Wei; Yu Liu; Li Liu
Scaling Compute Is Not All You Need for Adversarial Robustness. (93%)Edoardo Debenedetti; Zishen Wan; Maksym Andriushchenko; Vikash Sehwag; Kshitij Bhardwaj; Bhavya Kailkhura
Doubly Perturbed Task Free Continual Learning. (9%)Byung Hyun Lee; Min-hwan Oh; Se Young Chun
Interactive Visualization of Time-Varying Flow Fields Using Particle Tracing Neural Networks. (1%)Mengjiao Han; Jixian Li; Sudhanshu Sane; Shubham Gupta; Bei Wang; Steve Petruzza; Chris R. Johnson
2023-12-19
Tensor Train Decomposition for Adversarial Attacks on Computer Vision Models. (96%)Andrei Chertkov; Ivan Oseledets
Rethinking Randomized Smoothing from the Perspective of Scalability. (86%)Anupriya Kumari; Devansh Bhardwaj; Sukrit Jindal
SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks. (74%)Peishen Yan; Hao Wang; Tao Song; Yang Hua; Ruhui Ma; Ningxin Hu; Mohammad R. Haghighat; Haibing Guan
Progressive Poisoned Data Isolation for Training-time Backdoor Defense. (61%)Yiming Chen; Haiwei Wu; Jiantao Zhou
Adversarial AutoMixup. (11%)Huafeng Qin; Xin Jin; Yun Jiang; Mounim A. El-Yacoubi; Xinbo Gao
Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection. (1%)Gwladys Kelodjou; Laurence Rozé; Véronique Masson; Luis Galárraga; Romaric Gaudel; Maurice Tchuente; Alexandre Termier
I-CEE: Tailoring Explanations of Image Classifications Models to User Expertise. (1%)Yao Rong; Peizhu Qian; Vaibhav Unhelkar; Enkelejda Kasneci
2023-12-18
Gemini: A Family of Highly Capable Multimodal Models. (99%)Team Gemini; Rohan Anil; Sebastian Borgeaud; Yonghui Wu; Jean-Baptiste Alayrac; Jiahui Yu; Radu Soricut; Johan Schalkwyk; Andrew M. Dai; Anja Hauth; Katie Millican; David Silver; Slav Petrov; Melvin Johnson; Ioannis Antonoglou; Julian Schrittwieser; Amelia Glaese; Jilin Chen; Emily Pitler; Timothy Lillicrap; Angeliki Lazaridou; Orhan Firat; James Molloy; Michael Isard; Paul R. Barham; Tom Hennigan; Benjamin Lee; Fabio Viola; Malcolm Reynolds; Yuanzhong Xu; Ryan Doherty; Eli Collins; Clemens Meyer; Eliza Rutherford; Erica Moreira; Kareem Ayoub; Megha Goel; George Tucker; Enrique Piqueras; Maxim Krikun; Iain Barr; Nikolay Savinov; Ivo Danihelka; Becca Roelofs; Anaïs White; Anders Andreassen; Glehn Tamara von; Lakshman Yagati; Mehran Kazemi; Lucas Gonzalez; Misha Khalman; Jakub Sygnowski; Alexandre Frechette; Charlotte Smith; Laura Culp; Lev Proleev; Yi Luan; Xi Chen; James Lottes; Nathan Schucher; Federico Lebron; Alban Rrustemi; Natalie Clay; Phil Crone; Tomas Kocisky; Jeffrey Zhao; Bartek Perz; Dian Yu; Heidi Howard; Adam Bloniarz; Jack W. Rae; Han Lu; Laurent Sifre; Marcello Maggioni; Fred Alcober; Dan Garrette; Megan Barnes; Shantanu Thakoor; Jacob Austin; Gabriel Barth-Maron; William Wong; Rishabh Joshi; Rahma Chaabouni; Deeni Fatiha; Arun Ahuja; Ruibo Liu; Yunxuan Li; Sarah Cogan; Jeremy Chen; Chao Jia; Chenjie Gu; Qiao Zhang; Jordan Grimstad; Ale Jakse Hartman; Martin Chadwick; Gaurav Singh Tomar; Xavier Garcia; Evan Senter; Emanuel Taropa; Thanumalayan Sankaranarayana Pillai; Jacob Devlin; Michael Laskin; Diego de Las Casas; Dasha Valter; Connie Tao; Lorenzo Blanco; Adrià Puigdomènech Badia; David Reitter; Mianna Chen; Jenny Brennan; Clara Rivera; Sergey Brin; Shariq Iqbal; Gabriela Surita; Jane Labanowski; Abhi Rao; Stephanie Winkler; Emilio Parisotto; Yiming Gu; Kate Olszewska; Yujing Zhang; Ravi Addanki; Antoine Miech; Annie Louis; Laurent El Shafey; Denis Teplyashin; Geoff Brown; Elliot Catt; Nithya Attaluri; Jan Balaguer; Jackie Xiang; Pidong Wang; Zoe Ashwood; Anton Briukhov; Albert Webson; Sanjay Ganapathy; Smit Sanghavi; Ajay Kannan; Ming-Wei Chang; Axel Stjerngren; Josip Djolonga; Yuting Sun; Ankur Bapna; Matthew Aitchison; Pedram Pejman; Henryk Michalewski; Tianhe Yu; Cindy Wang; Juliette Love; Junwhan Ahn; Dawn Bloxwich; Kehang Han; Peter Humphreys; Thibault Sellam; James Bradbury; Varun Godbole; Sina Samangooei; Bogdan Damoc; Alex Kaskasoli; Sébastien M. R. Arnold; Vijay Vasudevan; Shubham Agrawal; Jason Riesa; Dmitry Lepikhin; Richard Tanburn; Srivatsan Srinivasan; Hyeontaek Lim; Sarah Hodkinson; Pranav Shyam; Johan Ferret; Steven Hand; Ankush Garg; Tom Le Paine; Jian Li; Yujia Li; Minh Giang; Alexander Neitz; Zaheer Abbas; Sarah York; Machel Reid; Elizabeth Cole; Aakanksha Chowdhery; Dipanjan Das; Dominika Rogozińska; Vitaly Nikolaev; Pablo Sprechmann; Zachary Nado; Lukas Zilka; Flavien Prost; Luheng He; Marianne Monteiro; Gaurav Mishra; Chris Welty; Josh Newlan; Dawei Jia; Miltiadis Allamanis; Clara Huiyi Hu; Liedekerke Raoul de; Justin Gilmer; Carl Saroufim; Shruti Rijhwani; Shaobo Hou; Disha Shrivastava; Anirudh Baddepudi; Alex Goldin; Adnan Ozturel; Albin Cassirer; Yunhan Xu; Daniel Sohn; Devendra Sachan; Reinald Kim Amplayo; Craig Swanson; Dessie Petrova; Shashi Narayan; Arthur Guez; Siddhartha Brahma; Jessica Landon; Miteyan Patel; Ruizhe Zhao; Kevin Villela; Luyu Wang; Wenhao Jia; Matthew Rahtz; Mai Giménez; Legg Yeung; Hanzhao Lin; James Keeling; Petko Georgiev; Diana Mincu; Boxi Wu; Salem Haykal; Rachel Saputro; Kiran Vodrahalli; James Qin; Zeynep Cankara; Abhanshu Sharma; Nick Fernando; Will Hawkins; Behnam Neyshabur; Solomon Kim; Adrian Hutter; Priyanka Agrawal; Alex Castro-Ros; George van den Driessche; Tao Wang; Fan Yang; Shuo-yiin Chang; Paul Komarek; Ross McIlroy; Mario Lučić; Guodong Zhang; Wael Farhan; Michael Sharman; Paul Natsev; Paul Michel; Yong Cheng; Yamini Bansal; Siyuan Qiao; Kris Cao; Siamak Shakeri; Christina Butterfield; Justin Chung; Paul Kishan Rubenstein; Shivani Agrawal; Arthur Mensch; Kedar Soparkar; Karel Lenc; Timothy Chung; Aedan Pope; Loren Maggiore; Jackie Kay; Priya Jhakra; Shibo Wang; Joshua Maynez; Mary Phuong; Taylor Tobin; Andrea Tacchetti; Maja Trebacz; Kevin Robinson; Yash Katariya; Sebastian Riedel; Paige Bailey; Kefan Xiao; Nimesh Ghelani; Lora Aroyo; Ambrose Slone; Neil Houlsby; Xuehan Xiong; Zhen Yang; Elena Gribovskaya; Jonas Adler; Mateo Wirth; Lisa Lee; Music Li; Thais Kagohara; Jay Pavagadhi; Sophie Bridgers; Anna Bortsova; Sanjay Ghemawat; Zafarali Ahmed; Tianqi Liu; Richard Powell; Vijay Bolina; Mariko Iinuma; Polina Zablotskaia; James Besley; Da-Woon Chung; Timothy Dozat; Ramona Comanescu; Xiance Si; Jeremy Greer; Guolong Su; Martin Polacek; Raphaël Lopez Kaufman; Simon Tokumine; Hexiang Hu; Elena Buchatskaya; Yingjie Miao; Mohamed Elhawaty; Aditya Siddhant; Nenad Tomasev; Jinwei Xing; Christina Greer; Helen Miller; Shereen Ashraf; Aurko Roy; Zizhao Zhang; Ada Ma; Angelos Filos; Milos Besta; Rory Blevins; Ted Klimenko; Chih-Kuan Yeh; Soravit Changpinyo; Jiaqi Mu; Oscar Chang; Mantas Pajarskas; Carrie Muir; Vered Cohen; Charline Le Lan; Krishna Haridasan; Amit Marathe; Steven Hansen; Sholto Douglas; Rajkumar Samuel; Mingqiu Wang; Sophia Austin; Chang Lan; Jiepu Jiang; Justin Chiu; Jaime Alonso Lorenzo; Lars Lowe Sjösund; Sébastien Cevey; Zach Gleicher; Thi Avrahami; Anudhyan Boral; Hansa Srinivasan; Vittorio Selo; Rhys May; Konstantinos Aisopos; Léonard Hussenot; Livio Baldini Soares; Kate Baumli; Michael B. Chang; Adrià Recasens; Ben Caine; Alexander Pritzel; Filip Pavetic; Fabio Pardo; Anita Gergely; Justin Frye; Vinay Ramasesh; Dan Horgan; Kartikeya Badola; Nora Kassner; Subhrajit Roy; Ethan Dyer; Víctor Campos; Alex Tomala; Yunhao Tang; Dalia El Badawy; Elspeth White; Basil Mustafa; Oran Lang; Abhishek Jindal; Sharad Vikram; Zhitao Gong; Sergi Caelles; Ross Hemsley; Gregory Thornton; Fangxiaoyu Feng; Wojciech Stokowiec; Ce Zheng; Phoebe Thacker; Çağlar Ünlü; Zhishuai Zhang; Mohammad Saleh; James Svensson; Max Bileschi; Piyush Patil; Ankesh Anand; Roman Ring; Katerina Tsihlas; Arpi Vezer; Marco Selvi; Toby Shevlane; Mikel Rodriguez; Tom Kwiatkowski; Samira Daruki; Keran Rong; Allan Dafoe; Nicholas FitzGerald; Keren Gu-Lemberg; Mina Khan; Lisa Anne Hendricks; Marie Pellat; Vladimir Feinberg; James Cobon-Kerr; Tara Sainath; Maribeth Rauh; Sayed Hadi Hashemi; Richard Ives; Yana Hasson; YaGuang Li; Eric Noland; Yuan Cao; Nathan Byrd; Le Hou; Qingze Wang; Thibault Sottiaux; Michela Paganini; Jean-Baptiste Lespiau; Alexandre Moufarek; Samer Hassan; Kaushik Shivakumar; Amersfoort Joost van; Amol Mandhane; Pratik Joshi; Anirudh Goyal; Matthew Tung; Andrew Brock; Hannah Sheahan; Vedant Misra; Cheng Li; Nemanja Rakićević; Mostafa Dehghani; Fangyu Liu; Sid Mittal; Junhyuk Oh; Seb Noury; Eren Sezener; Fantine Huot; Matthew Lamm; Cao Nicola De; Charlie Chen; Gamaleldin Elsayed; Ed Chi; Mahdis Mahdieh; Ian Tenney; Nan Hua; Ivan Petrychenko; Patrick Kane; Dylan Scandinaro; Rishub Jain; Jonathan Uesato; Romina Datta; Adam Sadovsky; Oskar Bunyan; Dominik Rabiej; Shimu Wu; John Zhang; Gautam Vasudevan; Edouard Leurent; Mahmoud Alnahlawi; Ionut Georgescu; Nan Wei; Ivy Zheng; Betty Chan; Pam G Rabinovitch; Piotr Stanczyk; Ye Zhang; David Steiner; Subhajit Naskar; Michael Azzam; Matthew Johnson; Adam Paszke; Chung-Cheng Chiu; Jaume Sanchez Elias; Afroz Mohiuddin; Faizan Muhammad; Jin Miao; Andrew Lee; Nino Vieillard; Sahitya Potluri; Jane Park; Elnaz Davoodi; Jiageng Zhang; Jeff Stanway; Drew Garmon; Abhijit Karmarkar; Zhe Dong; Jong Lee; Aviral Kumar; Luowei Zhou; Jonathan Evens; William Isaac; Zhe Chen; Johnson Jia; Anselm Levskaya; Zhenkai Zhu; Chris Gorgolewski; Peter Grabowski; Yu Mao; Alberto Magni; Kaisheng Yao; Javier Snaider; Norman Casagrande; Paul Suganthan; Evan Palmer; Geoffrey Irving; Edward Loper; Manaal Faruqui; Isha Arkatkar; Nanxin Chen; Izhak Shafran; Michael Fink; Alfonso Castaño; Irene Giannoumis; Wooyeol Kim; Mikołaj Rybiński; Ashwin Sreevatsa; Jennifer Prendki; David Soergel; Adrian Goedeckemeyer; Willi Gierke; Mohsen Jafari; Meenu Gaba; Jeremy Wiesner; Diana Gage Wright; Yawen Wei; Harsha Vashisht; Yana Kulizhskaya; Jay Hoover; Maigo Le; Lu Li; Chimezie Iwuanyanwu; Lu Liu; Kevin Ramirez; Andrey Khorlin; Albert Cui; Tian LIN; Marin Georgiev; Marcus Wu; Ricardo Aguilar; Keith Pallo; Abhishek Chakladar; Alena Repina; Xihui Wu; der Weide Tom van; Priya Ponnapalli; Caroline Kaplan; Jiri Simsa; Shuangfeng Li; Olivier Dousse; Fan Yang; Jeff Piper; Nathan Ie; Minnie Lui; Rama Pasumarthi; Nathan Lintz; Anitha Vijayakumar; Lam Nguyen Thiet; Daniel Andor; Pedro Valenzuela; Cosmin Paduraru; Daiyi Peng; Katherine Lee; Shuyuan Zhang; Somer Greene; Duc Dung Nguyen; Paula Kurylowicz; Sarmishta Velury; Sebastian Krause; Cassidy Hardin; Lucas Dixon; Lili Janzer; Kiam Choo; Ziqiang Feng; Biao Zhang; Achintya Singhal; Tejasi Latkar; Mingyang Zhang; Quoc Le; Elena Allica Abellan; Dayou Du; Dan McKinnon; Natasha Antropova; Tolga Bolukbasi; Orgad Keller; David Reid; Daniel Finchelstein; Maria Abi Raad; Remi Crocker; Peter Hawkins; Robert Dadashi; Colin Gaffney; Sid Lall; Ken Franko; Egor Filonov; Anna Bulanova; Rémi Leblond; Vikas Yadav; Shirley Chung; Harry Askham; Luis C. Cobo; Kelvin Xu; Felix Fischer; Jun Xu; Christina Sorokin; Chris Alberti; Chu-Cheng Lin; Colin Evans; Hao Zhou; Alek Dimitriev; Hannah Forbes; Dylan Banarse; Zora Tung; Jeremiah Liu; Mark Omernick; Colton Bishop; Chintu Kumar; Rachel Sterneck; Ryan Foley; Rohan Jain; Swaroop Mishra; Jiawei Xia; Taylor Bos; Geoffrey Cideron; Ehsan Amid; Francesco Piccinno; Xingyu Wang; Praseem Banzal; Petru Gurita; Hila Noga; Premal Shah; Daniel J. Mankowitz; Alex Polozov; Nate Kushman; Victoria Krakovna; Sasha Brown; MohammadHossein Bateni; Dennis Duan; Vlad Firoiu; Meghana Thotakuri; Tom Natan; Anhad Mohananey; Matthieu Geist; Sidharth Mudgal; Sertan Girgin; Hui Li; Jiayu Ye; Ofir Roval; Reiko Tojo; Michael Kwong; James Lee-Thorp; Christopher Yew; Quan Yuan; Sumit Bagri; Danila Sinopalnikov; Sabela Ramos; John Mellor; Abhishek Sharma; Aliaksei Severyn; Jonathan Lai; Kathy Wu; Heng-Tze Cheng; David Miller; Nicolas Sonnerat; Denis Vnukov; Rory Greig; Jennifer Beattie; Emily Caveness; Libin Bai; Julian Eisenschlos; Alex Korchemniy; Tomy Tsai; Mimi Jasarevic; Weize Kong; Phuong Dao; Zeyu Zheng; Frederick Liu; Fan Yang; Rui Zhu; Mark Geller; Tian Huey Teh; Jason Sanmiya; Evgeny Gladchenko; Nejc Trdin; Andrei Sozanschi; Daniel Toyama; Evan Rosen; Sasan Tavakkol; Linting Xue; Chen Elkind; Oliver Woodman; John Carpenter; George Papamakarios; Rupert Kemp; Sushant Kafle; Tanya Grunina; Rishika Sinha; Alice Talbert; Abhimanyu Goyal; Diane Wu; Denese Owusu-Afriyie; Cosmo Du; Chloe Thornton; Jordi Pont-Tuset; Pradyumna Narayana; Jing Li; Sabaer Fatehi; John Wieting; Omar Ajmeri; Benigno Uria; Tao Zhu; Yeongil Ko; Laura Knight; Amélie Héliou; Ning Niu; Shane Gu; Chenxi Pang; Dustin Tran; Yeqing Li; Nir Levine; Ariel Stolovich; Norbert Kalb; Rebeca Santamaria-Fernandez; Sonam Goenka; Wenny Yustalim; Robin Strudel; Ali Elqursh; Balaji Lakshminarayanan; Charlie Deck; Shyam Upadhyay; Hyo Lee; Mike Dusenberry; Zonglin Li; Xuezhi Wang; Kyle Levin; Raphael Hoffmann; Dan Holtmann-Rice; Olivier Bachem; Summer Yue; Sho Arora; Eric Malmi; Daniil Mirylenka; Qijun Tan; Christy Koh; Soheil Hassas Yeganeh; Siim Põder; Steven Zheng; Francesco Pongetti; Mukarram Tariq; Yanhua Sun; Lucian Ionita; Mojtaba Seyedhosseini; Pouya Tafti; Ragha Kotikalapudi; Zhiyu Liu; Anmol Gulati; Jasmine Liu; Xinyu Ye; Bart Chrzaszcz; Lily Wang; Nikhil Sethi; Tianrun Li; Ben Brown; Shreya Singh; Wei Fan; Aaron Parisi; Joe Stanton; Chenkai Kuang; Vinod Koverkathu; Christopher A. Choquette-Choo; Yunjie Li; TJ Lu; Abe Ittycheriah; Prakash Shroff; Pei Sun; Mani Varadarajan; Sanaz Bahargam; Rob Willoughby; David Gaddy; Ishita Dasgupta; Guillaume Desjardins; Marco Cornero; Brona Robenek; Bhavishya Mittal; Ben Albrecht; Ashish Shenoy; Fedor Moiseev; Henrik Jacobsson; Alireza Ghaffarkhah; Morgane Rivière; Alanna Walton; Clément Crepy; Alicia Parrish; Yuan Liu; Zongwei Zhou; Clement Farabet; Carey Radebaugh; Praveen Srinivasan; der Salm Claudia van; Andreas Fidjeland; Salvatore Scellato; Eri Latorre-Chimoto; Hanna Klimczak-Plucińska; David Bridson; Cesare Dario de; Tom Hudson; Piermaria Mendolicchio; Lexi Walker; Alex Morris; Ivo Penchev; Matthew Mauger; Alexey Guseynov; Alison Reid; Seth Odoom; Lucia Loher; Victor Cotruta; Madhavi Yenugula; Dominik Grewe; Anastasia Petrushkina; Tom Duerig; Antonio Sanchez; Steve Yadlowsky; Amy Shen; Amir Globerson; Adam Kurzrok; Lynette Webb; Sahil Dua; Dong Li; Preethi Lahoti; Surya Bhupatiraju; Dan Hurt; Haroon Qureshi; Ananth Agarwal; Tomer Shani; Matan Eyal; Anuj Khare; Shreyas Rammohan Belle; Lei Wang; Chetan Tekur; Mihir Sanjay Kale; Jinliang Wei; Ruoxin Sang; Brennan Saeta; Tyler Liechty; Yi Sun; Yao Zhao; Stephan Lee; Pandu Nayak; Doug Fritz; Manish Reddy Vuyyuru; John Aslanides; Nidhi Vyas; Martin Wicke; Xiao Ma; Taylan Bilal; Evgenii Eltyshev; Daniel Balle; Nina Martin; Hardie Cate; James Manyika; Keyvan Amiri; Yelin Kim; Xi Xiong; Kai Kang; Florian Luisier; Nilesh Tripuraneni; David Madras; Mandy Guo; Austin Waters; Oliver Wang; Joshua Ainslie; Jason Baldridge; Han Zhang; Garima Pruthi; Jakob Bauer; Feng Yang; Riham Mansour; Jason Gelman; Yang Xu; George Polovets; Ji Liu; Honglong Cai; Warren Chen; XiangHai Sheng; Emily Xue; Sherjil Ozair; Adams Yu; Christof Angermueller; Xiaowei Li; Weiren Wang; Julia Wiesinger; Emmanouil Koukoumidis; Yuan Tian; Anand Iyer; Madhu Gurumurthy; Mark Goldenson; Parashar Shah; MK Blake; Hongkun Yu; Anthony Urbanowicz; Jennimaria Palomaki; Chrisantha Fernando; Kevin Brooks; Ken Durden; Harsh Mehta; Nikola Momchev; Elahe Rahimtoroghi; Maria Georgaki; Amit Raul; Sebastian Ruder; Morgan Redshaw; Jinhyuk Lee; Komal Jalan; Dinghua Li; Ginger Perng; Blake Hechtman; Parker Schuh; Milad Nasr; Mia Chen; Kieran Milan; Vladimir Mikulik; Trevor Strohman; Juliana Franco; Tim Green; Demis Hassabis; Koray Kavukcuoglu; Jeffrey Dean; Oriol Vinyals
Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model. (99%)Decheng Liu; Xijun Wang; Chunlei Peng; Nannan Wang; Ruiming Hu; Xinbo Gao
The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations. (99%)Zebin Yun; Achi-Or Weingarten; Eyal Ronen; Mahmood Sharif
DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models. (16%)Jiachen Zhou; Peizhuo Lv; Yibing Lan; Guozhu Meng; Kai Chen; Hualong Ma
A Comprehensive Survey of Attack Techniques, Implementation, and Mitigation Strategies in Large Language Models. (10%)Aysan Esmradi; Daniel Wankit Yip; Chun Fai Chan
Model Stealing Attack against Recommender System. (10%)Zhihao Zhu; Rui Fan; Chenwang Wu; Yi Yang; Defu Lian; Enhong Chen
Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity. (4%)Zhihao Zhu; Chenwang Wu; Rui Fan; Yi Yang; Defu Lian; Enhong Chen
MISA: Unveiling the Vulnerabilities in Split Federated Learning. (1%)Wei Wan; Yuxuan Ning; Shengshan Hu; Lulu Xue; Minghui Li; Leo Yu Zhang; Hai Jin
A Survey of Side-Channel Attacks in Context of Cache -- Taxonomies, Analysis and Mitigation. (1%)Ankit Pulkit; Smita Naval; Vijay Laxmi
2023-12-17
UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks. (98%)Bingyin Zhao; Yingjie Lao
The Pros and Cons of Adversarial Robustness. (92%)Yacine Izza; Joao Marques-Silva
A Mutation-Based Method for Multi-Modal Jailbreaking Attack Detection. (80%)Xiaoyu Zhang; Cen Zhang; Tianlin Li; Yihao Huang; Xiaojun Jia; Xiaofei Xie; Yang Liu; Chao Shen
Robust Node Representation Learning via Graph Variational Diffusion Networks. (11%)Jun Zhuang; Mohammad Al Hasan
A Study on Transferability of Deep Learning Models for Network Intrusion Detection. (4%)Shreya Ghosh; Abu Shafin Mohammad Mahdee Jameel; Aly El Gamal
2023-12-16
Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off. (99%)Yu-An Liu; Ruqing Zhang; Mingkun Zhang; Wei Chen; Rijke Maarten de; Jiafeng Guo; Xueqi Cheng
Rethinking Robustness of Model Attributions. (80%)Sandesh Kamath; Sankalp Mittal; Amit Deshpande; Vineeth N Balasubramanian
SAME: Sample Reconstruction Against Model Extraction Attacks. (13%)Yi Xie; Jie Zhang; Shiqian Zhao; Tianwei Zhang; Xiaofeng Chen
TrojFair: Trojan Fairness Attacks. (8%)Mengxin Zheng; Jiaqi Xue; Yi Sheng; Lei Yang; Qian Lou; Lei Jiang
Transformers in Unsupervised Structure-from-Motion. (3%)Hemang Chawla; Arnav Varma; Elahe Arani; Bahram Zonooz
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning. (2%)Mengxin Zheng; Jiaqi Xue; Xun Chen; YanShan Wang; Qian Lou; Lei Jiang
2023-12-15
LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer. (99%)Yuxin Cao; Ziyu Zhao; Xi Xiao; Derui Wang; Minhui Xue; Jin Lu
Embodied Adversarial Attack: A Dynamic Robust Physical Attack in Autonomous Driving. (99%)Yitong Sun; Yao Huang; Xingxing Wei
Towards Transferable Targeted 3D Adversarial Attack in the Physical World. (99%)Yao Huang; Yinpeng Dong; Shouwei Ruan; Xiao Yang; Hang Su; Xingxing Wei
A Malware Classification Survey on Adversarial Attacks and Defences. (98%)Mahesh Datta Sai Ponnuru; Likhitha Amasala; Tanu Sree Bhimavarapu; Guna Chaitanya Garikipati
FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge. (76%)Jiahe Lan; Jie Wang; Baochen Yan; Zheng Yan; Elisa Bertino
Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs Against Query-Based Attacks. (74%)Pascal Zimmer; Sébastien Andreina; Giorgia Azzurra Marson; Ghassan Karame
Fragility, Robustness and Antifragility in Deep Learning. (67%)Chandresh Pravin; Ivan Martino; Giuseppe Nicosia; Varun Ojha
VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees. (67%)Anahita Baninajjar; Ahmed Rezine; Amir Aminifar
Silent Guardian: Protecting Text from Malicious Exploitation by Large Language Models. (10%)Jiawei Zhao; Kejiang Chen; Xiaojian Yuan; Yuang Qi; Weiming Zhang; Nenghai Yu
2023-12-14
AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection. (99%)Xiangtao Meng; Li Wang; Shanqing Guo; Lei Ju; Qingchuan Zhao
Continual Adversarial Defense. (95%)Qian Wang; Yaoyao Liu; Hefei Ling; Yingwei Li; Qihao Liu; Ping Li; Jiazhong Chen; Alan Yuille; Ning Yu
SlowTrack: Increasing the Latency of Camera-based Perception in Autonomous Driving Using Adversarial Examples. (92%)Chen Ma; Ningfei Wang; Qi Alfred Chen; Chao Shen
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks. (84%)Changjiang Li; Ren Pang; Bochuan Cao; Zhaohan Xi; Jinghui Chen; Shouling Ji; Ting Wang
Detection and Defense of Unlearnable Examples. (81%)Yifan Zhu; Lijia Yu; Xiao-Shan Gao
Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\infty$ Lipschitz Policy Networks. (81%)Buqing Nie; Jingtian Ji; Yangqing Fu; Yue Gao
Adversarial Robustness on Image Classification with $k$-means. (81%)Rollin Omari; Junae Kim; Paul Montague
Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey. (76%)Yichen Wan; Youyang Qu; Wei Ni; Yong Xiang; Longxiang Gao; Ekram Hossain
DRAM-Locker: A General-Purpose DRAM Protection Mechanism against Adversarial DNN Weight Attacks. (45%)Ranyang Zhou; Sabbir Ahmed; Arman Roohi; Adnan Siraj Rakin; Shaahin Angizi
No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models. (45%)Shengyao Zhang; Mi Zhang; Xudong Pan; Min Yang
Forbidden Facts: An Investigation of Competing Objectives in Llama-2. (45%)Tony T. Wang; Miles Wang; Kaivalya Hariharan; Nir Shavit
Coevolutionary Algorithm for Building Robust Decision Trees under Minimax Regret. (13%)Adam Żychowski; Andrew Perrault; Jacek Mańdziuk
Exploring Transferability for Randomized Smoothing. (5%)Kai Qiu; Huishuai Zhang; Zhirong Wu; Stephen Lin
Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting. (1%)Anthony Chen; Huanrui Yang; Yulu Gan; Denis A Gudovskiy; Zhen Dong; Haofan Wang; Tomoyuki Okuno; Yohei Nakata; Shanghang Zhang; Kurt Keutzer
2023-12-13
Defenses in Adversarial Machine Learning: A Survey. (99%)Baoyuan Wu; Shaokui Wei; Mingli Zhu; Meixi Zheng; Zihao Zhu; Mingda Zhang; Hongrui Chen; Danni Yuan; Li Liu; Qingshan Liu
Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purification. (99%)Xiaojun Xue; Chunxia Zhang; Tianxiang Xu; Zhendong Niu
Universal Adversarial Framework to Improve Adversarial Robustness for Diabetic Retinopathy Detection. (98%)Samrat Mukherjee; Dibyanayan Bandyopadhyay; Baban Gain; Asif Ekbal
Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks. (83%)Ao Liu; Wenshan Li; Tao Li; Beibei Li; Hanyuan Huang; Pan Zhou
Scalable Ensemble-based Detection Method against Adversarial Attacks for speaker verification. (64%)Haibin Wu; Heng-Cheng Kuo; Yu Tsao; Hung-yi Lee
Accelerating the Global Aggregation of Local Explanations. (47%)Alon Mor; Yonatan Belinkov; Benny Kimelfeld
Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking. (22%)Shengsheng Qian; Dizhan Xue; Yifei Wang; Shengjie Zhang; Huaiwen Zhang; Changsheng Xu
Efficient Representation of the Activation Space in Deep Neural Networks. (11%)Tanya Akumu; Celia Cintas; Girmaw Abebe Tadesse; Adebayo Oshingbesan; Skyler Speakman; Edward III McFowland
Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models. (1%)Jiang Zhang; Qiong Wu; Yiming Xu; Cheng Cao; Zheng Du; Konstantinos Psounis
2023-12-12
Radio Signal Classification by Adversarially Robust Quantum Machine Learning. (99%)Yanqiu Wu; Eromanga Adermann; Chandra Thapa; Seyit Camtepe; Hajime Suzuki; Muhammad Usman
SSTA: Salient Spatially Transformed Attack. (99%)Renyang Liu; Wei Zhou; Sixin Wu; Jun Zhao; Kwok-Yan Lam
DTA: Distribution Transform-based Attack for Query-Limited Scenario. (99%)Renyang Liu; Wei Zhou; Xin Jin; Song Gao; Yuanyu Wang; Ruxin Wang
May the Noise be with you: Adversarial Training without Adversarial Examples. (98%)Ayoub Arous; Andres F Lopez-Lopera; Nael Abu-Ghazaleh; Ihsen Alouani
Collapse-Oriented Adversarial Training with Triplet Decoupling for Robust Image Retrieval. (98%)Qiwei Tian; Chenhao Lin; Qian Li; Zhengyu Zhao; Chao Shen
Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training. (98%)Qian Li; Yuxiao Hu; Yinpeng Dong; Dongxiao Zhang; Yuntian Chen
QuadAttack: A Quadratic Programming Approach to Ordered Top-K Attacks. (97%)Thomas Paniagua; Ryan Grainger; Tianfu Wu
Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detection. (92%)Jonathan J. Y. Kim; Martin Urschler; Patricia J. Riddle; Jorg S. Wicker
ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning. (86%)Xiangyu Yin; Sihao Wu; Jiaxu Liu; Meng Fang; Xingyu Zhao; Xiaowei Huang; Wenjie Ruan
Robust MRI Reconstruction by Smoothed Unrolling (SMUG). (82%)Shijun Liang; Van Hoang Minh Nguyen; Jinghan Jia; Ismail Alkhouri; Sijia Liu; Saiprasad Ravishankar
Cost Aware Untargeted Poisoning Attack against Graph Neural Networks,. (70%)Yuwei Han; Yuni Lai; Yulin Zhu; Kai Zhou
EdgePruner: Poisoned Edge Pruning in Graph Contrastive Learning. (47%)Hiroya Kato; Kento Hasegawa; Seira Hidano; Kazuhide Fukushima
Causality Analysis for Evaluating the Security of Large Language Models. (22%)Wei Zhao; Zhe Li; Jun Sun
SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models. (13%)Feifei Wang; Zhentao Tan; Tianyi Wei; Yue Wu; Qidong Huang
Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass Safety Filters of Text-to-Image Models. (8%)Yimo Deng; Huangxun Chen
Eroding Trust In Aerial Imagery: Comprehensive Analysis and Evaluation Of Adversarial Attacks In Geospatial Systems. (5%)Michael Lanier; Aayush Dhakal; Zhexiao Xiong; Arthur Li; Nathan Jacobs; Yevgeniy Vorobeychik
Securing Graph Neural Networks in MLaaS: A Comprehensive Realization of Query-based Integrity Verification. (2%)Bang Wu; Xingliang Yuan; Shuo Wang; Qi Li; Minhui Xue; Shirui Pan
Majority is Not Required: A Rational Analysis of the Private Double-Spend Attack from a Sub-Majority Adversary. (1%)Yanni Georghiades; Rajesh Mishra; Karl Kreder; Sriram Vishwanath
Rethinking Model Inversion Attacks With Patch-Wise Reconstruction. (1%)Jonggyu Jang; Hyeonsu Lyu; Hyun Jong Yang
2023-12-11
Towards Transferable Adversarial Attacks with Centralized Perturbation. (99%)Shangbo Wu; Yu-an Tan; Yajie Wang; Ruinan Ma; Wencong Ma; Yuanzhang Li
MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks. (98%)Yuyang Zhou; Guang Cheng; Zongyao Chen; Shui Yu
Sparse but Strong: Crafting Adversarially Robust Graph Lottery Tickets. (83%)Subhajit Dutta Chowdhury; Zhiyu Ni; Qingyuan Peng; Souvik Kundu; Pierluigi Nuzzo
Reward Certification for Policy Smoothed Reinforcement Learning. (78%)Ronghui Mu; Leandro Soriano Marcolino; Tianle Zhang; Yanghao Zhang; Xiaowei Huang; Wenjie Ruan
Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks. (31%)Danni Yuan; Shaokui Wei; Mingda Zhang; Li Liu; Baoyuan Wu
Poisoned ChatGPT Finds Work for Idle Hands: Exploring Developers' Coding Practices with Insecure Suggestions from Poisoned AI Models. (22%)Sanghak Oh; Kiho Lee; Seonhye Park; Doowon Kim; Hyoungshick Kim
Promoting Counterfactual Robustness through Diversity. (13%)Francesco Leofante; Nico Potyka
Resilient Path Planning for UAVs in Data Collection under Adversarial Attacks. (10%)Xueyuan Wang; M. Cenk Gursoy
Adversarial Camera Patch: An Effective and Robust Physical-World Attack on Object Detectors. (1%)Kalibinuer Tiliwalidi
Robust Graph Neural Network based on Graph Denoising. (1%)Victor M. Tenorio; Samuel Rey; Antonio G. Marques
2023-12-10
Data-Free Hard-Label Robustness Stealing Attack. (86%)Xiaojian Yuan; Kejiang Chen; Wen Huang; Jie Zhang; Weiming Zhang; Nenghai Yu
A Practical Survey on Emerging Threats from AI-driven Voice Attacks: How Vulnerable are Commercial Voice Control Systems? (76%)Yuanda Wang; Qiben Yan; Nikolay Ivanov; Xun Chen
An Ambiguity Measure for Recognizing the Unknowns in Deep Learning. (12%)Roozbeh Yousefzadeh
METAL: Metamorphic Testing Framework for Analyzing Large-Language Model Qualities. (2%)Sangwon Hyun; Mingyu Guo; M. Ali Babar
2023-12-09
Poisoning $\times$ Evasion: Symbiotic Adversarial Robustness for Graph Neural Networks. (99%)Ege Erdogan; Simon Geisler; Stephan Günnemann
Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation. (98%)Shiji Zhao; Ranjie Duan; Xizhe Wang; Xingxing Wei
Dynamic Adversarial Attacks on Autonomous Driving Systems. (98%)Amirhosein Chahe; Chenan Wang; Abhishek Jeyapratap; Kaidi Xu; Lifeng Zhou
Initialization Matters for Adversarial Transfer Learning. (76%)Andong Hua; Jindong Gu; Zhiyu Xue; Nicholas Carlini; Eric Wong; Yao Qin
2023-12-08
HC-Ref: Hierarchical Constrained Refinement for Robust Adversarial Training of GNNs. (99%)Xiaobing Pei; Haoran Yang; Gang Shen
SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation. (99%)Bangyan He; Xiaojun Jia; Siyuan Liang; Tianrui Lou; Yang Liu; Xiaochun Cao
MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness. (99%)Xiaoyun Xu; Shujian Yu; Jingzheng Wu; Stjepan Picek
BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting. (96%)Huming Qiu; Junjie Sun; Mi Zhang; Xudong Pan; Min Yang
An adversarial attack approach for eXplainable AI evaluation on deepfake detection models. (38%)Balachandar Gowrisankar; Vrizlynn L. L. Thing
A Red Teaming Framework for Securing AI in Maritime Autonomous Systems. (3%)Mathew J. Walter; Aaron Barrett; Kimberly Tam
Annotation-Free Group Robustness via Loss-Based Resampling. (2%)Mahdi Ghaznavi; Hesam Asadollahzadeh; HamidReza Yaghoubi Araghi; Fahimeh Hosseini Noohdani; Mohammad Hossein Rohban; Mahdieh Soleymani Baghshah
HuRef: HUman-REadable Fingerprint for Large Language Models. (2%)Boyi Zeng; Lizheng Wang; Yuncong Hu; Yi Xu; Chenghu Zhou; Xinbing Wang; Yu Yu; Zhouhan Lin
Topology-Based Reconstruction Prevention for Decentralised Learning. (1%)Florine W. Delft University of Technology, the Netherlands and Dekker; Zekeriya Delft University of Technology, the Netherlands and Erkin; Mauro Università di Padova, Italy Delft University of Technology, the Netherlands and Conti
2023-12-07
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model. (99%)Kaiyu Song; Hanjiang Lai
OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization. (99%)Dongchen Han; Xiaojun Jia; Yang Bai; Jindong Gu; Yang Liu; Xiaochun Cao
Diffence: Fencing Membership Privacy With Diffusion Models. (97%)Yuefeng Peng; Ali Naseh; Amir Houmansadr
FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning. (70%)Hossein Fereidooni; Alessandro Pegoraro; Phillip Rieger; Alexandra Dmitrienko; Ahmad-Reza Sadeghi
Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks. (64%)Shuli Jiang; Swanand Ravindra Kadhe; Yi Zhou; Ling Cai; Nathalie Baracaldo
DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions. (15%)Fangzhou Wu; Xiaogeng Liu; Chaowei Xiao
2023-12-06
Defense against ML-based Power Side-channel Attacks on DNN Accelerators with Adversarial Attacks. (98%)Xiaobei Yan; Chip Hong Chang; Tianwei Zhang
Defense Against Adversarial Attacks using Convolutional Auto-Encoders. (97%)Shreyasi Mandal
Node-aware Bi-smoothing: Certified Robustness against Graph Injection Attacks. (88%)Yuni Lai; Yulin Zhu; Bailin Pan; Kai Zhou
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training. (54%)Jaehyung Kim; Yuning Mao; Rui Hou; Hanchao Yu; Davis Liang; Pascale Fung; Qifan Wang; Fuli Feng; Lifu Huang; Madian Khabsa
Detecting Voice Cloning Attacks via Timbre Watermarking. (13%)Chang Liu; Jie Zhang; Tianwei Zhang; Xi Yang; Weiming Zhang; Nenghai Yu
Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models. (11%)Sze Jue Yang; Chinh D. La; Quang H. Nguyen; Eugene Bagdasaryan; Kok-Seng Wong; Anh Tuan Tran; Chee Seng Chan; Khoa D. Doan
Dr. Jekyll and Mr. Hyde: Two Faces of LLMs. (4%)Matteo Gioele Collu; Tom Janssen-Groesbeek; Stefanos Koffas; Mauro Conti; Stjepan Picek
MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator. (2%)Xiao-Yin Liu; Xiao-Hu Zhou; Guo-Tao Li; Hao Li; Mei-Jiang Gui; Tian-Yu Xiang; De-Xing Huang; Zeng-Guang Hou
2023-12-05
Generating Visually Realistic Adversarial Patch. (99%)Xiaosen Wang; Kunyu Wang
A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System. (99%)Xinwei Yuan; Shu Han; Wei Huang; Hongliang Ye; Xianglong Kong; Fan Zhang
Realistic Scatterer Based Adversarial Attacks on SAR Image Classifiers. (99%)Tian Ye; Rajgopal Kannan; Viktor Prasanna; Carl Busart; Lance Kaplan
ScAR: Scaling Adversarial Robustness for LiDAR Object Detection. (99%)Xiaohu Lu; Hayder Radha
Class Incremental Learning for Adversarial Robustness. (98%)Seungju Cho; Hongsin Lee; Changick Kim
Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More. (89%)Jan Schuchardt; Yan Scholten; Stephan Günnemann
On the Robustness of Large Multimodal Models Against Image Adversarial Attacks. (69%)Xuanimng Cui; Alejandro Aparcedo; Young Kyun Jang; Ser-Nam Lim
Scaling Laws for Adversarial Attacks on Language Model Activations. (50%)Stanislav Fort
Indirect Gradient Matching for Adversarial Robust Distillation. (13%)Hongsin Lee; Seungju Cho; Changick Kim
Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics. (3%)Xiaoxing Mo; Yechao Zhang; Leo Yu Zhang; Wei Luo; Nan Sun; Shengshan Hu; Shang Gao; Yang Xiang
Prompt Optimization via Adversarial In-Context Learning. (3%)Xuan Long Do; Yiran Zhao; Hannah Brown; Yuxi Xie; James Xu Zhao; Nancy F. Chen; Kenji Kawaguchi; Michael Qizhe Xie; Junxian He
Privacy-Preserving Task-Oriented Semantic Communications Against Model Inversion Attacks. (2%)Yanhu Wang; Shuaishuai Guo; Yiqin Deng; Haixia Zhang; Yuguang Fang
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning. (2%)Zhuo Huang; Chang Liu; Yinpeng Dong; Hang Su; Shibao Zheng; Tongliang Liu
2023-12-04
Adversarial Medical Image with Hierarchical Feature Hiding. (99%)Qingsong Yao; Zecheng He; Yuexiang Li; Yi Lin; Kai Ma; Yefeng Zheng; S. Kevin Zhou
InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models. (99%)Xunguang Wang; Zhenlan Ji; Pingchuan Ma; Zongjie Li; Shuai Wang
Singular Regularization with Information Bottleneck Improves Model's Adversarial Robustness. (98%)Guanlin Li; Naishan Zheng; Man Zhou; Jie Zhang; Tianwei Zhang
Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical world. (12%)Chengyin Hu; Weiwen Shi
Auto DP-SGD: Dual Improvements of Privacy and Accuracy via Automatic Clipping Threshold and Noise Multiplier Estimation. (1%)Sai Venkatesh Chilukoti; Md Imran Hossen; Liqun Shan; Vijay Srinivas Tida; Xiai Hei
Rejuvenating image-GPT as Strong Visual Representation Learners. (1%)Sucheng Ren; Zeyu Wang; Hongru Zhu; Junfei Xiao; Alan Yuille; Cihang Xie
2023-12-03
QuantAttack: Exploiting Dynamic Quantization to Attack Vision Transformers. (99%)Amit Baras; Alon Zolfi; Yuval Elovici; Asaf Shabtai
OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection. (61%)Haoyu Jiang; Haiyang Yu; Nan Li; Ping Yi
Evaluating the Security of Satellite Systems. (16%)Roy Peled; Eran Aizikovich; Edan Habler; Yuval Elovici; Asaf Shabtai
Exploring Adversarial Robustness of LiDAR-Camera Fusion Model in Autonomous Driving. (13%)Bo Yang; Xiaoyu Ji; Xiaoyu Ji; Xiaoyu Ji; Xiaoyu Ji
Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger. (2%)Yiming Li; Mingyan Zhu; Junfeng Guo; Tao Wei; Shu-Tao Xia; Zhan Qin
2023-12-02
TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation. (99%)Xiaojun Jia; Jindong Gu; Yihao Huang; Simeng Qin; Qing Guo; Yang Liu; Xiaochun Cao
Rethinking PGD Attack: Is Sign Function Necessary? (98%)Junjie Yang; Tianlong Chen; Xuxi Chen; Zhangyang Wang; Yingbin Liang
PROFL: A Privacy-Preserving Federated Learning Method with Stringent Defense Against Poisoning Attacks. (61%)Yisheng Zhong; Li-Ping Wang
Mendata: A Framework to Purify Manipulated Training Data. (2%)Zonghao Huang; Neil Gong; Michael K. Reiter
2023-12-01
PyraTrans: Learning Attention-Enriched Multi-Scale Pyramid Network from Pre-Trained Transformers for Effective Malicious URL Detection. (69%)Ruitong Liu; Yanbin Wang; Zhenhao Guo; Haitao Xu; Zhan Qin; Wenrui Ma; Fan Zhang
Survey of Security Issues in Memristor-based Machine Learning Accelerators for RF Analysis. (22%)William Lillis; Max Cohen Hoffing; Wayne Burleson
Deep Generative Attacks and Countermeasures for Data-Driven Offline Signature Verification. (10%)An Ngo; MinhPhuong Cao; Rajesh Kumar
The Philosopher's Stone: Trojaning Plugins of Large Language Models. (4%)Tian Dong; Minhui Xue; Guoxing Chen; Rayne Holland; Yan Meng; Shaofeng Li; Zhen Liu; Haojin Zhu
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training. (1%)Yefan Zhou; Tianyu Pang; Keqin Liu; Charles H. Martin; Michael W. Mahoney; Yaoqing Yang
Crystal: Enhancing Blockchain Mining Transparency with Quorum Certificate. (1%)Jianyu Niu; Fangyu Gai; Runchao Han; Ren Zhang; Yinqian Zhang; Chen Feng
2023-11-30
Improving the Robustness of Quantized Deep Neural Networks to White-Box Attacks using Stochastic Quantization and Information-Theoretic Ensemble Training. (98%)Saurabh Farkya; Aswin Raghavan; Avi Ziskind
Adversarial Attacks and Defenses for Wireless Signal Classifiers using CDI-aware GANs. (98%)Sujata Sinha; Alkan Soysal
Universal Backdoor Attacks. (97%)Benjamin Schneider; Nils Lukas; Florian Kerschbaum
Fool the Hydra: Adversarial Attacks against Multi-view Object Detection Systems. (97%)Bilel Tarchoun; Quazi Mishkatul Alam; Nael Abu-Ghazaleh; Ihsen Alouani
Corrupting Convolution-based Unlearnable Datasets with Pixel-based Image Transformations. (88%)Xianlong Wang; Shengshan Hu; Minghui Li; Zhifei Yu; Ziqi Zhou; Leo Yu Zhang; Hai Jin
Optimal Attack and Defense for Reinforcement Learning. (76%)Jeremy McMahan; Young Wu; Xiaojin Zhu; Qiaomin Xie
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion? (74%)Zhengyue Zhao; Jinhao Duan; Kaidi Xu; Chenan Wang; Rui Zhangp Zidong Dup Qi Guo; Xing Hu
Improving Adversarial Transferability via Model Alignment. (68%)Avery Ma; Amir-massoud Farahmand; Yangchen Pan; Philip Torr; Jindong Gu
Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approach. (62%)Kai Li; Jingjing Zheng; Xin Yuan; Wei Ni; Ozgur B. Akan; H. Vincent Poor
Mark My Words: Analyzing and Evaluating Language Model Watermarks. (9%)Julien Piet; Chawin Sitawarin; Vivian Fang; Norman Mu; David Wagner
2023-11-29
Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention. (98%)Lujia Shen; Yuwen Pu; Shouling Ji; Changjiang Li; Xuhong Zhang; Chunpeng Ge; Ting Wang
Group-wise Sparse and Explainable Adversarial Attacks. (96%)Shpresim Sadiku; Moritz Wagner; Sebastian Pokutta
Quantum Neural Networks under Depolarization Noise: Exploring White-Box Attacks and Defenses. (88%)David Winderl; Nicola Franco; Jeanette Miriam Lorenz
On the Adversarial Robustness of Graph Contrastive Learning Methods. (83%)Filippo Guerranti; Zinuo Yi; Anna Starovoit; Rafiq Kamel; Simon Geisler; Stephan Günnemann
Adversarial Robust Memory-Based Continual Learner. (81%)Xiaoyue Mi; Fan Tang; Zonghan Yang; Danding Wang; Juan Cao; Peng Li; Yang Liu
Improving Faithfulness for Vision Transformers. (80%)Lijie Hu; Yixin Liu; Ninghao Liu; Mengdi Huai; Lichao Sun; Di Wang
TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4. (68%)Zihao Tan; Qingliang Chen; Yongjian Huang; Chen Liang
Topology-Preserving Adversarial Training. (10%)Xiaoyue Mi; Fan Tang; Yepeng Weng; Danding Wang; Juan Cao; Sheng Tang; Peng Li; Yang Liu
Query-Relevant Images Jailbreak Large Multi-Modal Models. (9%)Xin Liu; Yichen Zhu; Yunshi Lan; Chao Yang; Yu Qiao
Analyzing and Explaining Image Classifiers via Diffusion Guidance. (8%)Maximilian Augustin; Yannic Neuhaus; Matthias Hein
Poisoning Attacks Against Contrastive Recommender Systems. (2%)Zongwei Wang; Junliang Yu; Min Gao; Hongzhi Yin; Bin Cui; Shazia Sadiq
SenTest: Evaluating Robustness of Sentence Encoders. (2%)Tanmay Chavan; Shantanu Patankar; Aditya Kane; Omkar Gokhale; Geetanjali Kale; Raviraj Joshi
Critical Influence of Overparameterization on Sharpness-aware Minimization. (1%)Sungbin Shin; Dongyeop Lee; Maksym Andriushchenko; Namhoon Lee
CLIPC8: Face liveness detection algorithm based on image-text pairs and contrastive learning. (1%)Xu Liu; Shu Zhou; Yurong Song; Wenzhe Luo; Xin Zhang
Unveiling the Implicit Toxicity in Large Language Models. (1%)Jiaxin Wen; Pei Ke; Hao Sun; Zhexin Zhang; Chengfei Li; Jinfeng Bai; Minlie Huang
2023-11-28
Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks. (99%)Lucas Beerens; Desmond J. Higham
NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields. (99%)Xiaoliang Liu; Furao Shen; Feng Han; Jian Zhao; Changhai Nie
Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model. (98%)AprilPyone MaungMaung; Isao Echizen; Hitoshi Kiya
RADAP: A Robust and Adaptive Defense Against Diverse Adversarial Patches on Face Recognition. (92%)Xiaoliang Liu; Furao Shen; Jian Zhao; Changhai Nie
STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers. (26%)Daqian Shao; Lukas Fesser; Marta Kwiatkowska
1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness. (13%)Bernd Prach; Fabio Brau; Giorgio Buttazzo; Christoph H. Lampert
Scalable Extraction of Training Data from (Production) Language Models. (10%)Milad Nasr; Nicholas Carlini; Jonathan Hayase; Matthew Jagielski; A. Feder Cooper; Daphne Ippolito; Christopher A. Choquette-Choo; Eric Wallace; Florian Tramèr; Katherine Lee
Cooperative Abnormal Node Detection with Adversary Resistance. (10%)Yingying Huangfu; Tian Bai
On robust overfitting: adversarial training induced distribution matters. (1%)Runzhi Tian; Yongyi Mao
Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations. (1%)Maximilian Dreyer; Reduan Achtibat; Wojciech Samek; Sebastian Lapuschkin
Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now. (1%)Ayush Sarkar; Hanlin Mai; Amitabh Mahapatra; Svetlana Lazebnik; D. A. Forsyth; Anand Bhattad
Enhancing Cyber-Resilience in Integrated Energy System Scheduling with Demand Response Using Deep Reinforcement Learning. (1%)Yang Li; Wenjie Ma; Yuanzheng Li; Sen Li; Zhe Chen; Mohammad Shahidehpor
2023-11-27
RetouchUAA: Unconstrained Adversarial Attack via Image Retouching. (99%)Mengda Xie; Yiling He; Meie Fang
Adversaral Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights. (99%)Ryoya Nara; Yusuke Matsui
Rethinking Mixup for Improving the Adversarial Transferability. (98%)Xiaosen Wang; Zeyuan Yin
Instruct2Attack: Language-Guided Semantic Adversarial Attacks. (98%)Jiang Liu; Chen Wei; Yuxiang Guo; Heng Yu; Alan Yuille; Soheil Feizi; Chun Pong Lau; Rama Chellappa
CLAP: Contrastive Learning with Augmented Prompts for Robustness on Pretrained Vision-Language Models. (95%)Yichao Cai; Yuhang Liu; Zhen Zhang; Javen Qinfeng Shi
A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective. (50%)Xianghua Xie; Chen Hu; Hanchi Ren; Jingjing Deng
Threshold Breaker: Can Counter-Based RowHammer Prevention Mechanisms Truly Safeguard DRAM? (31%)Ranyang Zhou; Jacqueline Liu; Sabbir Ahmed; Nakul Kochar; Adnan Siraj Rakin; Shaahin Angizi
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift. (31%)Shengwei An; Sheng-Yen Chou; Kaiyuan Zhang; Qiuling Xu; Guanhong Tao; Guangyu Shen; Siyuan Cheng; Shiqing Ma; Pin-Yu Chen; Tsung-Yi Ho; Xiangyu Zhang
Distributed Attacks over Federated Reinforcement Learning-enabled Cell Sleep Control. (22%)Han Zhang; Hao Zhou; Medhat Elsayed; Majid Bavand; Raimundas Gaigalas; Yigit Ozcan; Melike Erol-Kantarci
"Do Users fall for Real Adversarial Phishing?" Investigating the Human response to Evasive Webpages. (15%)Ajka Draganovic; Savino Dambra; Javier Aldana Iuit; Kevin Roundy; Giovanni Apruzzese
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs. (12%)Haoqin Tu; Chenhang Cui; Zijun Wang; Yiyang Zhou; Bingchen Zhao; Junlin Han; Wangchunshu Zhou; Huaxiu Yao; Cihang Xie
Microarchitectural Security of AWS Firecracker VMM for Serverless Cloud Platforms. (1%)Zane Worcester Polytechnic Institute Weissman; Thore University of Lübeck Tiemann; Thomas University of Lübeck Eisenbarth; Berk Worcester Polytechnic Institute Sunar
2023-11-26
Adversarial Purification of Information Masking. (99%)Sitong Liu; Zhichao Lian; Shuangquan Zhang; Liang Xiao
Having Second Thoughts? Let's hear it. (56%)Jung H. Lee; Sujith Vijayan
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP. (13%)Jiawang Bai; Kuofeng Gao; Shaobo Min; Shu-Tao Xia; Zhifeng Li; Wei Liu
Confidence Is All You Need for MI Attacks. (2%)Abhishek Sinha; Himanshi Tibrewal; Mansi Gupta; Nikhar Waghela; Shivank Garg
2023-11-25
Mixing Classifiers to Alleviate the Accuracy-Robustness Trade-Off. (68%)Yatong Bai; Brendon G. Anderson; Somayeh Sojoudi
Robust Graph Neural Networks via Unbiased Aggregation. (12%)Ruiqi Feng; Zhichao Hou; Tyler Derr; Xiaorui Liu
Effective Backdoor Mitigation Depends on the Pre-training Objective. (10%)Sahil Verma; Gantavya Bhatt; Avi Schwarzschild; Soumye Singhal; Arnav Mohanty Das; Chirag Shah; John P Dickerson; Jeff Bilmes
2023-11-24
Trainwreck: A damaging adversarial attack on image classifiers. (99%)Jan Zahálka
Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models. (96%)Francesco Croce; Matthias Hein
Universal Jailbreak Backdoors from Poisoned Human Feedback. (1%)Javier Rando; Florian Tramèr
2023-11-23
When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence. (99%)Benoit Coqueret; Mathieu Carbone; Olivier Sentieys; Gabriel Zaid
Adversarial defense based on distribution transfer. (99%)Jiahao Chen; Diqun Yan; Li Dong
Robust and Interpretable COVID-19 Diagnosis on Chest X-ray Images using Adversarial Training. (68%)Karina Yang; Alexis Bennett; Dominique Duncan
Presentation Attack Detection using Convolutional Neural Networks and Local Binary Patterns. (1%)Justin Spencer; Deborah Lawrence; Prosenjit Chatterjee; Kaushik Roy; Albert Esterline; Jung-Hee Kim
2023-11-22
A Survey of Adversarial CAPTCHAs on its History, Classification and Generation. (99%)Zisheng Xu; Qiao Yan; F. Richard Yu; Victor C. M. Leung
Transfer Attacks and Defenses for Large Language Models on Coding Tasks. (99%)Chi Zhang; Zifan Wang; Ravi Mangal; Matt Fredrikson; Limin Jia; Corina Pasareanu
Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization. (98%)Yuzhe You; Jarvis Tse; Jian Zhao
Hard Label Black Box Node Injection Attack on Graph Neural Networks. (93%)Yu Zhou; Zihao Dong; Guofeng Zhang; Jingchen Tang
Security and Privacy Challenges in Deep Learning Models. (74%)Gopichandh Golla
A Somewhat Robust Image Watermark against Diffusion-based Editing Models. (50%)Mingtian Tan; Tianhao Wang; Somesh Jha
OASIS: Offsetting Active Reconstruction Attacks in Federated Learning. (15%)Tre' R. Jeter; Truc Nguyen; Raed Alharbi; My T. Thai
Unified Classification and Rejection: A One-versus-All Framework. (1%)Zhen Cheng; Xu-Yao Zhang; Cheng-Lin Liu
2023-11-21
SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion. (96%)Yueqian Lin; Jingyang Zhang; Yiran Chen; Hai Li
Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise. (96%)Yixin Liu; Kaidi Xu; Xun Chen; Lichao Sun
Attention Deficit is Ordered! Fooling Deformable Vision Transformers with Collaborative Adversarial Patches. (75%)Quazi Mishkatul Alam; Bilel Tarchoun; Ihsen Alouani; Nael Abu-Ghazaleh
Attacking Motion Planners Using Adversarial Perception Errors. (69%)Jonathan Sadeghi; Nicholas A. Lord; John Redford; Romain Mueller
Toward Robust Imperceptible Perturbation against Unauthorized Text-to-image Diffusion-based Synthesis. (62%)Yixin Liu; Chenrui Fan; Yutong Dai; Xun Chen; Pan Zhou; Lichao Sun
Iris Presentation Attack: Assessing the Impact of Combining Vanadium Dioxide Films with Artificial Eyes. (1%)Darshika Jauhari; Renu Sharma; Cunjian Chen; Nelson Sepulveda; Arun Ross
2023-11-20
ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches. (99%)Nandish Chattopadhyay; Amira Guesmi; Muhammad Abdullah Hanif; Bassem Ouni; Muhammad Shafique
DefensiveDR: Defending against Adversarial Patches using Dimensionality Reduction. (99%)Nandish Chattopadhyay; Amira Guesmi; Muhammad Abdullah Hanif; Bassem Ouni; Muhammad Shafique
Generating Valid and Natural Adversarial Examples with Large Language Models. (99%)Zimu Wang; Wei Wang; Qi Chen; Qiufeng Wang; Anh Nguyen
AdvGen: Physical Adversarial Attack on Face Presentation Attack Detection Systems. (99%)Sai Amrit Patnaik; Shivali Chansoriya; Anil K. Jain; Anoop M. Namboodiri
Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems. (50%)Guangjing Wang; Ce Zhou; Yuanda Wang; Bocheng Chen; Hanqing Guo; Qiben Yan
Understanding Variation in Subpopulation Susceptibility to Poisoning Attacks. (15%)Evan Rose; Fnu Suya; David Evans
Training robust and generalizable quantum models. (10%)Julian Berberich; Daniel Fink; Daniel Pranjić; Christian Tutschku; Christian Holm
BrainWash: A Poisoning Attack to Forget in Continual Learning. (4%)Ali Abbasi; Parsa Nooralinejad; Hamed Pirsiavash; Soheil Kolouri
2023-11-19
Adversarial Prompt Tuning for Vision-Language Models. (98%)Jiaming Zhang; Xingjun Ma; Xin Wang; Lingyu Qiu; Jiaqi Wang; Yu-Gang Jiang; Jitao Sang
Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information. (78%)Zhengmian Hu; Gang Wu; Saayan Mitra; Ruiyi Zhang; Tong Sun; Heng Huang; Viswanathan Swaminathan
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning. (69%)Siyuan Liang; Mingli Zhu; Aishan Liu; Baoyuan Wu; Xiaochun Cao; Ee-Chien Chang
EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models. (10%)Ruoxi Chen; Haibo Jin; Jinyin Chen; Lichao Sun
2023-11-18
Boost Adversarial Transferability by Uniform Scale and Mix Mask Method. (99%)Tao Wang; Zijian Ying; Qianmu Li; zhichao Lian
Improving Adversarial Transferability by Stable Diffusion. (99%)Jiayang Liu; Siyu Zhu; Siyuan Liang; Jie Zhang; Han Fang; Weiming Zhang; Ee-Chien Chang
Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications. (92%)Giulio Rossolini; Alessandro Biondi; Giorgio Buttazzo
TextGuard: Provable Defense against Backdoor Attacks on Text Classification. (82%)Hengzhi Pei; Jinyuan Jia; Wenbo Guo; Bo Li; Dawn Song
Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies. (1%)Feng Wang; M. Cenk Gursoy; Senem Velipasalar
2023-11-17
Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models. (97%)Hee-Seon Kim; Minji Son; Minbeom Kim; Myung-Joon Kwon; Changick Kim
PACOL: Poisoning Attacks Against Continual Learners. (93%)Huayu Li; Gregory Ditzler
Two-Factor Authentication Approach Based on Behavior Patterns for Defeating Puppet Attacks. (1%)Wenhao Wang; Guyue Li; Zhiming Chu; Haobo Li; Daniele Faccio
2023-11-16
Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting. (99%)Romain Ilbert; Thai V. Hoang; Zonghua Zhang; Themis Palpanas
Hijacking Large Language Models via Adversarial In-Context Learning. (92%)Yao Qiang; Xiangyu Zhou; Dongxiao Zhu
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking. (54%)Nan Xu; Fei Wang; Ben Zhou; Bang Zheng Li; Chaowei Xiao; Muhao Chen
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations. (38%)Wenjie Mo; Jiashu Xu; Qin Liu; Jiongxiao Wang; Jun Yan; Chaowei Xiao; Muhao Chen
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models. (16%)Jiongxiao Wang; Junlin Wu; Muhao Chen; Yevgeniy Vorobeychik; Chaowei Xiao
Towards Improving Robustness Against Common Corruptions using Mixture of Class Specific Experts. (2%)Shashank Kotyan; Danilo Vasconcellos Vargas
Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities. (2%)Avishree Khare; Saikat Dutta; Ziyang Li; Alaia Solko-Breslin; Rajeev Alur; Mayur Naik
Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework. (2%)Matthew Pisano; Peter Ly; Abraham Sanders; Bingsheng Yao; Dakuo Wang; Tomek Strzalkowski; Mei Si
Towards more Practical Threat Models in Artificial Intelligence Security. (2%)Kathrin Grosse; Lukas Bieringer; Tarek Richard Besold; Alexandre Alahi
You Cannot Escape Me: Detecting Evasions of SIEM Rules in Enterprise Networks. (1%)Rafael Uetz; Marco Herzog; Louis Hackländer; Simon Schwarz; Martin Henze
2023-11-15
Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts. (99%)Yuanwei Wu; Xiang Li; Yixin Liu; Pan Zhou; Lichao Sun
Backdoor Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment. (74%)Haoran Wang; Kai Shu
Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing. (64%)A K Iowa State University Nirala; A New York University Joshi; C New York University Hegde; S Iowa State University Sarkar
Adversarially Robust Spiking Neural Networks Through Conversion. (61%)Ozan Özdenizci; Robert Legenstein
How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities. (16%)Lingbo Mo; Boshi Wang; Muhao Chen; Huan Sun
Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization. (16%)Zhexin Zhang; Junxiao Yang; Pei Ke; Fei Mi; Hongning Wang; Minlie Huang
Privacy Threats in Stable Diffusion Models. (13%)Thomas Cilloni; Charles Fleming; Charles Walter
MirrorNet: A TEE-Friendly Framework for Secure On-device DNN Inference. (2%)Ziyu Liu; Yukui Luo; Shijin Duan; Tong Zhou; Xiaolin Xu
JAB: Joint Adversarial Prompting and Belief Augmentation. (1%)Ninareh Mehrabi; Palash Goyal; Anil Ramakrishna; Jwala Dhamala; Shalini Ghosh; Richard Zemel; Kai-Wei Chang; Aram Galstyan; Rahul Gupta
Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models. (1%)Yueqing Liang; Lu Cheng; Ali Payani; Kai Shu
2023-11-14
Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning. (99%)Shashank Kotyan; Danilo Vasconcellos Vargas
Physical Adversarial Examples for Multi-Camera Systems. (99%)Ana Răduţoiu; Jan-Philipp Schulze; Philip Sperl; Konstantin Böttinger
DALA: A Distribution-Aware LoRA-Based Adversarial Attack against Language Models. (99%)Yibo Wang; Xiangjue Dong; James Caverlee; Philip S. Yu
On The Relationship Between Universal Adversarial Attacks And Sparse Representations. (98%)Dana Weitzner; Raja Giryes
A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily. (62%)Peng Ding; Jun Kuang; Dan Ma; Xuezhi Cao; Yunsen Xian; Jiajun Chen; Shujian Huang
Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets. (26%)Vatsal Gupta; Pranshu Pandya; Tushar Kataria; Vivek Gupta; Dan Roth
The Perception-Robustness Tradeoff in Deterministic Image Restoration. (1%)Guy Ohayon; Tomer Michaeli; Michael Elad
2023-11-13
Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models. (99%)Yuanbin Cheng; Koji Yamashita; Jim Follum; Nanpeng Yu
Parrot-Trained Adversarial Examples: Pushing the Practicality of Black-Box Audio Attacks against Speaker Recognition Models. (99%)Rui Duan; Zhe Qu; Leah Ding; Yao Liu; Zhuo Lu
An Extensive Study on Adversarial Attack against Pre-trained Models of Code. (99%)Xiaohu Du; Ming Wen; Zichao Wei; Shangwen Wang; Hai Jin
Multi-agent Attacks for Black-box Social Recommendations. (96%)Wenqi Fan; Shijie Wang; Xiao-yong Wei; Xiaowei Mei; Shanru Lin; Qing Li
On the Robustness of Neural Collapse and the Neural Collapse of Robustness. (87%)Jingtong Su; Ya Shi Zhang; Nikolaos Tsilivis; Julia Kempe
Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data. (70%)Bart Pleiter; Behrad Tajalli; Stefanos Koffas; Gorka Abad; Jing Xu; Martha Larson; Stjepan Picek
2023-11-12
Learning Globally Optimized Language Structure via Adversarial Training. (83%)Xuwang Yin
Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach. (70%)Moshe Eliasof; Davide Murari; Ferdia Sherry; Carola-Bibiane Schönlieb
Analytical Verification of Deep Neural Network Performance for Time-Synchronized Distribution System State Estimation. (5%)Behrouz Azimian; Shiva Moshtagh; Anamitra Pal; Shanshan Ma
DialMAT: Dialogue-Enabled Transformer with Moment-Based Adversarial Training. (1%)Kanta Kaneda; Ryosuke Korekata; Yuiga Wada; Shunya Nagashima; Motonari Kambara; Yui Iioka; Haruka Matsuo; Yuto Imai; Takayuki Nishimura; Komei Sugiura
2023-11-11
Robust Text Classification: Analyzing Prototype-Based Networks. (97%)Zhivar Sourati; Darshan Deshpande; Filip Ilievski; Kiril Gashteovski; Sascha Saralajew
2023-11-10
Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous. (99%)Ziwei Wang; Nabil Aouf; Jose Pizarro; Christophe Honvault
Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches. (99%)Jianan Feng; Jiachun Li; Changqing Miao; Jianjun Huang; Wei You; Wenchang Shi; Bin Liang
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness. (99%)Mingyuan Fan; Xiaodan Li; Cen Chen; Wenmeng Zhou; Yaliang Li
Resilient and constrained consensus against adversarial attacks: A distributed MPC framework. (84%)Henglai Wei; Kunwu Zhang; Hui Zhang; Yang Shi
CALLOC: Curriculum Adversarial Learning for Secure and Robust Indoor Localization. (1%)Danish Gufran; Sudeep Pasricha
Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration. (1%)Wenjie Fu; Huandong Wang; Chen Gao; Guanghua Liu; Yong Li; Tao Jiang
2023-11-09
ABIGX: A Unified Framework for eXplainable Fault Detection and Classification. (68%)Yue Zhuo; Jinchuan Qian; Zhihuan Song; Zhiqiang Ge
Honest Score Client Selection Scheme: Preventing Federated Learning Label Flipping Attacks in Non-IID Scenarios. (50%)Yanli Li; Huaming Chen; Wei Bao; Zhengmeng Xu; Dong Yuan
Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction. (15%)Shanghao Shi; Ning Wang; Yang Xiao; Chaoyu Zhang; Yi Shi; Y. Thomas Hou; Wenjing Lou
FigStep: Jailbreaking Large Vision-language Models via Typographic Visual Prompts. (1%)Yichen Gong; Delong Ran; Jinyuan Liu; Conglei Wang; Tianshuo Cong; Anyu Wang; Sisi Duan; Xiaoyun Wang
FireMatch: A Semi-Supervised Video Fire Detection Network Based on Consistency and Distribution Alignment. (1%)Qinghua Lin; Zuoyong Li; Kun Zeng; Haoyi Fan; Wei Li; Xiaoguang Zhou
2023-11-08
Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data. (99%)Thibault Simonetto; Salah Ghamizi; Antoine Desjardins; Maxime Cordy; Yves Le Traon
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection. (70%)Akshit Jindal; Vikram Goyal; Saket Anand; Chetan Arora
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5? (61%)C. Daniel Freeman; Laura Culp; Aaron Parisi; Maxwell L Bileschi; Gamaleldin F Elsayed; Alex Rizkowsky; Isabelle Simpson; Alex Alemi; Azade Nova; Ben Adlam; Bernd Bohnet; Gaurav Mishra; Hanie Sedghi; Igor Mordatch; Izzeddin Gur; Jaehoon Lee; JD Co-Reyes; Jeffrey Pennington; Kelvin Xu; Kevin Swersky; Kshiteej Mahajan; Lechao Xiao; Rosanne Liu; Simon Kornblith; Noah Constant; Peter J. Liu; Roman Novak; Yundi Qian; Noah Fiedel; Jascha Sohl-Dickstein
SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training. (10%)Rui Xu; Wenkang Qin; Peixiang Huang; Haowang; Lin Luo
Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning. (1%)Muhammad Akhtar Munir; Muhammad Haris Khan; M. Saquib Sarfraz; Mohsen Ali
Counter-Empirical Attacking based on Adversarial Reinforcement Learning for Time-Relevant Scoring System. (1%)Xiangguo Sun; Hong Cheng; Hang Dong; Bo Qiao; Si Qin; Qingwei Lin
2023-11-07
Unveiling Safety Vulnerabilities of Large Language Models. (61%)George Kour; Marcel Zalmanovici; Naama Zwerdling; Esther Goldbraich; Ora Nova Fandina; Ateret Anaby-Tavor; Orna Raz; Eitan Farchi
When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers through Membership Inference Attacks. (10%)Huan Tian; Guangsheng Zhang; Bo Liu; Tianqing Zhu; Ming Ding; Wanlei Zhou
Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications. (2%)Fengqing Jiang; Zhangchen Xu; Luyao Niu; Boxin Wang; Jinyuan Jia; Bo Li; Radha Poovendran
SoK: Security Below the OS -- A Security Analysis of UEFI. (1%)Priyanka Prakash Surve; Oleg Brodt; Mark Yampolskiy; Yuval Elovici; Asaf Shabtai
Do LLMs exhibit human-like response biases? A case study in survey design. (1%)Lindia Tjuatja; Valerie Chen; Sherry Tongshuang Wu; Ameet Talwalkar; Graham Neubig
2023-11-06
Measuring Adversarial Datasets. (92%)Yuanchen Bai; Raoyi Huang; Vijay Viswanathan; Tzu-Sheng Kuo; Tongshuang Wu
Can LLMs Follow Simple Rules? (68%)Norman Mu; Sarah Chen; Zifan Wang; Sizhe Chen; David Karamardian; Lulwa Aljeraisy; Basel Alomair; Dan Hendrycks; David Wagner
Preserving Privacy in GANs Against Membership Inference Attack. (33%)Mohammadhadi Shateri; Francisco Messina; Fabrice Labeau; Pablo Piantanida
Cal-DETR: Calibrated Detection Transformer. (4%)Muhammad Akhtar Munir; Salman Khan; Muhammad Haris Khan; Mohsen Ali; Fahad Shahbaz Khan
2023-11-05
ELEGANT: Certified Defense on the Fairness of Graph Neural Networks. (10%)Yushun Dong; Binchi Zhang; Hanghang Tong; Jundong Li
2023-11-04
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models. (74%)Zhuoshi Pan; Yuguang Yao; Gaowen Liu; Bingquan Shen; H. Vicky Zhao; Ramana Rao Kompella; Sijia Liu
2023-11-03
Efficient Black-Box Adversarial Attacks on Neural Text Detectors. (22%)Vitalii Fishchuk; Daniel Braun
The Alignment Problem in Context. (2%)Raphaël Millière
2023-11-02
Adversary ML Resilience in Autonomous Driving Through Human Centered Perception Mechanisms. (99%)Aakriti Shah
Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly. (99%)Qizhang Li; Yiwen Guo; Wangmeng Zuo; Hao Chen
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game. (93%)Sam Toyer; Olivia Watkins; Ethan Adrian Mendes; Justin Svegliato; Luke Bailey; Tiffany Wang; Isaac Ong; Karim Elmaaroufi; Pieter Abbeel; Trevor Darrell; Alan Ritter; Stuart Russell
On the Lipschitz constant of random neural networks. (92%)Paul Geuchen; Thomas Heindl; Dominik Stöger; Felix Voigtlaender
Universal Perturbation-based Secret Key-Controlled Data Hiding. (80%)Donghua Wang; Wen Yao; Tingsong Jiang; Xiaoqian Chen
Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models. (76%)Andy Zhou; Jindong Wang; Yu-Xiong Wang; Haohan Wang
Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Prediction. (13%)Abhijith Sharma; Phil Munz; Apurva Narayan
Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula. (12%)Aryaman Reddi; Maximilian Tölle; Jan Peters; Georgia Chalvatzaki; Carlo D'Eramo
Sequential Subset Matching for Dataset Distillation. (1%)Jiawei Du; Qin Shi; Joey Tianyi Zhou
E(2) Equivariant Neural Networks for Robust Galaxy Morphology Classification. (1%)Sneh Pandya; Purvik Patel; Franc O; Jonathan Blazek
Robust Identity Perceptual Watermark Against Deepfake Face Swapping. (1%)Tianyi Wang; Mengxiao Huang; Harry Cheng; Bin Ma; Yinglong Wang
2023-11-01
NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks. (99%)Seokil Ham; Jungwuk Park; Dong-Jun Han; Jaekyun Moon
Adversarial Examples in the Physical World: A Survey. (98%)Jiakai Wang; Donghua Wang; Jin Hu; Siyang Wu; Tingsong Jiang; Wen Yao; Aishan Liu; Xianglong Liu
Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems. (80%)Ziqing Lu; Guanlin Liu; Lifeng Cai; Weiyu Xu
Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation. (76%)Shashank Kotyan; Danilo Vasconcellos Vargas
MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training. (75%)Jiacheng Li; Ninghui Li; Bruno Ribeiro
Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks. (1%)Yichen Huang; Timothy Baldwin
Open-Set Face Recognition with Maximal Entropy and Objectosphere Loss. (1%)Rafael Henrique Vareto; Yu Linghu; Terrance E. Boult; William Robson Schwartz; Manuel Günther
2023-10-31
Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning. (99%)Haoyu Liu; Alec F. Diallo; Paul Patras
Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield. (99%)Jinhwa Kim; Ali Derakhshan; Ian G. Harris
LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations. (99%)Kunyu Wang; Juluan Shi; Wenxuan Wang
Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems. (98%)Jung-Woo Chang; Ke Sun; Nasimeh Heydaribeni; Seira Hidano; Xinyu Zhang; Farinaz Koushanfar
Is Robustness Transferable across Languages in Multilingual Neural Machine Translation? (26%)Leiyu Pan; Supryadi; Deyi Xiong
Dynamic Batch Norm Statistics Update for Natural Robustness. (22%)Shahbaz Rezaei; Mohammad Sadegh Norouzzadeh
In Search of Lost Online Test-time Adaptation: A Survey. (1%)Zixin Wang; Yadan Luo; Liang Zheng; Zhuoxiao Chen; Sen Wang; Zi Huang
2023-10-30
Label-Only Model Inversion Attacks via Knowledge Transfer. (83%)Ngoc-Bao Nguyen; Keshigeyan Chandrasegaran; Milad Abdollahzadeh; Ngai-Man Cheung
Exploring Geometry of Blind Spots in Vision Models. (83%)Sriram Balasubramanian; Gaurang Sriramanan; Vinu Sankar Sadasivan; Soheil Feizi
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats. (74%)Leo Schwinn; David Dobre; Stephan Günnemann; Gauthier Gidel
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models. (61%)Minxing Zhang; Ning Yu; Rui Wen; Michael Backes; Yang Zhang
Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustness. (33%)Ahmad-Reza Ehyaei; Golnoosh Farnadi; Samira Samadi
Differentially Private Reward Estimation with Preference Feedback. (16%)Sayak Ray Chowdhury; Xingyu Zhou; Nagarajan Natarajan
Asymmetric Diffusion Based Channel-Adaptive Secure Wireless Semantic Communications. (10%)Xintian Ren; Jun Wu; Hansong Xu; Qianqian Pan
Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection. (1%)Swanand Ravindra Kadhe; Heiko Ludwig; Nathalie Baracaldo; Alan King; Yi Zhou; Keith Houck; Ambrish Rawat; Mark Purcell; Naoise Holohan; Mikio Takeuchi; Ryo Kawahara; Nir Drucker; Hayim Shaul; Eyal Kushnir; Omri Soceanu
2023-10-29
Blacksmith: Fast Adversarial Training of Vision Transformers via a Mixture of Single-step and Multi-step Methods. (99%)Mahdi Salmani; Alireza Dehghanpour Farashah; Mohammad Azizmalayeri; Mahdi Amiri; Navid Eslami; Mohammad Taghi Manzuri; Mohammad Hossein Rohban
Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors. (98%)Han Liu; Xingshuo Huang; Xiaotong Zhang; Qimai Li; Fenglong Ma; Wei Wang; Hongyang Chen; Hong Yu; Xianchao Zhang
BERT Lost Patience Won't Be Robust to Adversarial Slowdown. (98%)Zachary Coalson; Gabriel Ritter; Rakesh Bobba; Sanghyun Hong
Adversarial Examples Are Not Real Features. (98%)Ang Li; Yifei Wang; Yiwen Guo; Yisen Wang
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI. (82%)Bochuan Cao; Changjiang Li; Ting Wang; Jinyuan Jia; Bo Li; Jinghui Chen
Poisoning Retrieval Corpora by Injecting Adversarial Passages. (68%)Zexuan Zhong; Ziqing Huang; Alexander Wettig; Danqi Chen
Label Poisoning is All You Need. (54%)Rishi D. Jha; Jonathan Hayase; Sewoong Oh
Robustifying Language Models with Test-Time Adaptation. (47%)Noah Thomas McDermott; Junfeng Yang; Chengzhi Mao
Path Analysis for Effective Fault Localization in Deep Neural Networks. (1%)Soroush Hashemifar; Saeed Parsa; Akram Kalaee
From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude. (1%)Sayak Saha Roy; Poojitha Thota; Krishna Vamsi Naragam; Shirin Nilizadeh
2023-10-28
Assessing and Improving Syntactic Adversarial Robustness of Pre-trained Models for Code Translation. (92%)Guang Yang; Yu Zhou; Xiangyu Zhang; Xiang Chen; Tingting Han; Taolue Chen
Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness. (86%)Soumyendu Sarkar; Ashwin Ramesh Babu; Sajad Mousavi; Zachariah Carmichael; Vineet Gundecha; Sahand Ghorbanpour; Ricardo Luna; Gutierrez Antonio Guillen; Avisek Naug
Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness. (61%)Boya Zhang; Weijian Luo; Zhihua Zhang
Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers. (47%)Wencong You; Zayd Hammoudeh; Daniel Lowd
Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation. (10%)Kunlin Cai; Jinghuai Zhang; Will Shand; Zhiqing Hong; Guang Wang; Desheng Zhang; Jianfeng Chi; Yuan Tian
2023-10-27
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification. (99%)Mintong Kang; Dawn Song; Bo Li
Understanding and Improving Ensemble Adversarial Defense. (99%)Yian Deng; Tingting Mu
LipSim: A Provably Robust Perceptual Similarity Metric. (45%)Sara Ghazanfari; Alexandre Araujo; Prashanth Krishnamurthy; Farshad Khorrami; Siddharth Garg
Elevating Code-mixed Text Handling through Auditory Information of Words. (5%)Mamta; Zishan Ahmad; Asif Ekbal
Understanding Parameter Saliency via Extreme Value Theory. (1%)Shuo Wang; Issei Sato
2023-10-26
Unscrambling the Rectification of Adversarial Attacks Transferability across Computer Networks. (99%)Ehsan Nowroozi; Samaneh Ghelichkhani; Imran Haider; Ali Dehghantanha
A Survey on Transferability of Adversarial Examples across Deep Neural Networks. (99%)Jindong Gu; Xiaojun Jia; Jorge Pau de; Wenqain Yu; Xinwei Liu; Avery Ma; Yuan Xun; Anjun Hu; Ashkan Khakzar; Zhijiang Li; Xiaochun Cao; Philip Torr
Defending Against Transfer Attacks From Public Models. (99%)Chawin Sitawarin; Jaewon Chang; David Huang; Wesson Altoyan; David Wagner
Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation. (93%)Kira Maag; Asja Fischer
Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow. (93%)Erik Scheurer; Jenny Schmalfuss; Alexander Lis; Andrés Bruhn
CBD: A Certified Backdoor Detector Based on Local Dominant Probability. (76%)Zhen Xiang; Zidi Xiong; Bo Li
SoK: Pitfalls in Evaluating Black-Box Attacks. (76%)Fnu Suya; Anshuman Suri; Tingwei Zhang; Jingtao Hong; Yuan Tian; David Evans
Instability of computer vision models is a necessary result of the task itself. (26%)Oliver Turnbull; George Cevora
PAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descent. (1%)Guangliang Liu; Zhiyu Xue; Xitong Zhang; Kristen Marie Johnson; Rongrong Wang
A minimax optimal control approach for robust neural ODEs. (1%)Cristina Cipriani; Alessandro Scagliotti; Tobias Wöhrer
2023-10-25
Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks. (93%)Aradhana Sinha; Ananth Balashankar; Ahmad Beirami; Thi Avrahami; Jilin Chen; Alex Beutel
Trust, but Verify: Robust Image Segmentation using Deep Learning. (54%)Fahim Ahmed Zaman; Xiaodong Wu; Weiyu Xu; Milan Sonka; Raghuraman Mudumbai
Dual Defense: Adversarial, Traceable, and Invisible Robust Watermarking against Face Swapping. (26%)Yunming Zhang; Dengpan Ye; Caiyun Xie; Long Tang; Chuanxi Chen; Ziyi Liu; Jiacheng Deng
On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts. (22%)Yixin Wu; Ning Yu; Michael Backes; Yun Shen; Yang Zhang
Wide Flat Minimum Watermarking for Robust Ownership Verification of GANs. (12%)Jianwei Fei; Zhihua Xia; Benedetta Tondi; Mauro Barni
Multi-scale Diffusion Denoised Smoothing. (1%)Jongheon Jeong; Jinwoo Shin
SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation. (1%)Qianxu Wang; Haotong Zhang; Congyue Deng; Yang You; Hao Dong; Yixin Zhu; Leonidas Guibas
2023-10-24
Adversarial sample generation and training using geometric masks for accurate and resilient license plate character recognition. (99%)Bishal Shrestha; Griwan Khakurel; Kritika Simkhada; Badri Adhikari
RAEDiff: Denoising Diffusion Probabilistic Models Based Reversible Adversarial Examples Self-Generation and Self-Recovery. (92%)Fan Xing; Xiaoyi Zhou; Xuefeng Fan; Zhuo Tian; Yan Zhao
Defense Against Model Extraction Attacks on Recommender Systems. (92%)Sixiao Zhang; Hongzhi Yin; Hongxu Chen; Cheng Long
Segue: Side-information Guided Generative Unlearnable Examples for Facial Privacy Protection in Real World. (89%)Zhiling Zhang; Jie Zhang; Kui Zhang; Wenbo Zhou; Weiming Zhang; Nenghai Yu
Hierarchical Randomized Smoothing. (75%)Yan Scholten; Jan Schuchardt; Aleksandar Bojchevski; Stephan Günnemann
Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks. (73%)Yang Chen; Stjepan Picek; Zhonglin Ye; Zhaoyang Wang; Haixing Zhao
Corrupting Neuron Explanations of Deep Visual Features. (41%)Divyansh Srivastava; Tuomas Oikarinen; Tsui-Wei Weng
Improving Robustness and Reliability in Medical Image Classification with Latent-Guided Diffusion and Nested-Ensembles. (13%)Xing Shen; Hengguan Huang; Brennan Nichyporuk; Tal Arbel
Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers. (10%)Mosh Levy; Shauli Ravfogel; Yoav Goldberg
A Survey on Detection of LLMs-Generated Content. (1%)Xianjun Yang; Liangming Pan; Xuandong Zhao; Haifeng Chen; Linda Petzold; William Yang Wang; Wei Cheng
White-box Compiler Fuzzing Empowered by Large Language Models. (1%)Chenyuan Yang; Yinlin Deng; Runyu Lu; Jiayi Yao; Jiawei Liu; Reyhaneh Jabbarvand; Lingming Zhang
Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation. (1%)Jiexin Wang; Liuwen Cao; Xitong Luo; Zhiping Zhou; Jiayuan Xie; Adam Jatowt; Yi Cai
2023-10-23
Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval. (99%)Xu Yuan; Zheng Zhang; Xunguang Wang; Lin Wu
F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns. (99%)Yaguan Qian; Chenyu Zhao; Zhaoquan Gu; Bin Wang; Shouling Ji; Wei Wang; Boyang Zhou; Pan Zhou
AutoDAN: Automatic and Interpretable Adversarial Attacks on Large Language Models. (98%)Sicheng Zhu; Ruiyi Zhang; Bang An; Gang Wu; Joe Barrow; Zichao Wang; Furong Huang; Ani Nenkova; Tong Sun
Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks. (98%)Xiaojun Jia; Jianshu Li; Jindong Gu; Yang Bai; Xiaochun Cao
On the Detection of Image-Scaling Attacks in Machine Learning. (15%)Erwin Quiring; Andreas Müller; Konrad Rieck
Unleashing the potential of prompt engineering: a comprehensive review. (1%)Banghao Chen; Zhaofeng Zhang; Nicolas Langrené; Shengxin Zhu
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions. (1%)Lingdong Kong; Shaoyuan Xie; Hanjiang Hu; Lai Xing Ng; Benoit R. Cottereau; Wei Tsang Ooi
Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift. (1%)Mouxiang Chen; Lefei Shen; Han Fu; Zhuo Li; Jianling Sun; Chenghao Liu
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks. (1%)Xiaoyi Chen; Siyuan Tang; Rui Zhu; Shijun Yan; Lei Jin; Zihao Wang; Liya Su; Zhikun Zhang; XiaoFeng Wang; Haixu Tang
2023-10-22
Diffusion-Based Adversarial Purification for Speaker Verification. (99%)Yibo Bai; Xiao-Lei Zhang
CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability. (99%)Minxuan Lv; Chengwei Dai; Kun Li; Wei Zhou; Songlin Hu
Imperceptible CMOS camera dazzle for adversarial attacks on deep neural networks. (92%)Zvi Stein; Adrian Stern
ADoPT: LiDAR Spoofing Attack Detection Based on Point-Level Temporal Consistency. (26%)Minkyoung Cho; Yulong Cao; Zixiang Zhou; Z. Morley Mao
Attention-Enhancing Backdoor Attacks Against BERT-based Models. (13%)Weimin Lyu; Songzhu Zheng; Lu Pang; Haibin Ling; Chao Chen
MoPe: Model Perturbation-based Privacy Attacks on Language Models. (9%)Marvin Li; Jason Wang; Jeffrey Wang; Seth Neel
Reputation-Based Federated Learning Defense to Mitigate Threats in EEG Signal Classification. (1%)Zhibo Zhang; Pengfei Li; Ahmed Y. Al Hammadi; Fusen Guo; Ernesto Damiani; Chan Yeob Yeun
2023-10-21
Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces. (99%)Ayberk Aydin; Alptekin Temizel
Training Image Derivatives: Increased Accuracy and Universal Robustness. (5%)Vsevolod I. Avrutskiy
2023-10-20
Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting. (99%)Zecheng Tang; Kaifeng Qi; Juntao Li; Min Zhang
An LLM can Fool Itself: A Prompt-Based Adversarial Attack. (99%)Xilie Xu; Keyi Kong; Ning Liu; Lizhen Cui; Di Wang; Jingfeng Zhang; Mohan Kankanhalli
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models. (61%)Shawn Shan; Wenxin Ding; Josephine Passananti; Haitao Zheng; Ben Y. Zhao
The Hidden Adversarial Vulnerabilities of Medical Federated Learning. (45%)Erfan Darzi; Florian Dubost; Nanna. M. Sijtsema; Ooijen P. M. A van
Adversarial Attacks on Fairness of Graph Neural Networks. (26%)Binchi Zhang; Yushun Dong; Chen Chen; Yada Zhu; Minnan Luo; Jundong Li
FLTracer: Accurate Poisoning Attack Provenance in Federated Learning. (26%)Xinyu Zhang; Qingyu Liu; Zhongjie Ba; Yuan Hong; Tianhang Zheng; Feng Lin; Li Lu; Kui Ren
Can We Trust the Similarity Measurement in Federated Learning? (15%)Zhilin Wang; Qin Hu; Xukai Zou
Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images. (4%)Logan Frank; Jim Davis
VOICE-ZEUS: Impersonating Zoom's E2EE-Protected Static Media and Textual Communications via Simple Voice Manipulations. (4%)Mashari Alatawi; Nitesh Saxena
2023-10-19
Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks. (98%)Xiaodong Yu; Hao Cheng; Xiaodong Liu; Dan Roth; Jianfeng Gao
Generating Robust Adversarial Examples against Online Social Networks (OSNs). (98%)Jun Liu; Jiantao Zhou; Haiwei Wu; Weiwei Sun; Jinyu Tian
Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial Examples. (98%)Jun Liu; Jiantao Zhou; Jinyu Tian; Weiwei Sun
Learn from the Past: A Proxy based Adversarial Defense Framework to Boost Robustness. (98%)Yaohua Liu; Jiaxin Gao; Zhu Liu; Xianghao Jiao; Xin Fan; Risheng Liu
OODRobustBench: benchmarking and analyzing adversarial robustness under distribution shift. (97%)Lin Li; Yifei Wang; Chawin Sitawarin; Michael Spratling
PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses. (97%)Chong Xiang; Tong Wu; Sihui Dai; Jonathan Petit; Suman Jana; Prateek Mittal
Prompt Injection Attacks and Defenses in LLM-Integrated Applications. (47%)Yupei Liu; Yuqi Jia; Runpeng Geng; Jinyuan Jia; Neil Zhenqiang Gong
Attack Prompt Generation for Red Teaming and Defending Large Language Models. (15%)Boyi Deng; Wenjie Wang; Fuli Feng; Yang Deng; Qifan Wang; Xiangnan He
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models. (5%)Boyang Zhang; Zheng Li; Ziqing Yang; Xinlei He; Michael Backes; Mario Fritz; Yang Zhang
To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets. (1%)Darshil Doshi; Aritra Das; Tianyu He; Andrey Gromov
Detecting Shared Data Manipulation in Distributed Optimization Algorithms. (1%)Mohannad Alkhraijah; Rachel Harris; Samuel Litchfield; David Huggins; Daniel K. Molzahn
Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models. (1%)Jianwei Li; Qi Lei; Wei Cheng; Dongkuan Xu
2023-10-18
Exploring Decision-based Black-box Attacks on Face Forgery Detection. (99%)Zhaoyu Chen; Bo Li; Kaixun Jiang; Shuang Wu; Shouhong Ding; Wenqiang Zhang
Segment Anything Meets Universal Adversarial Perturbation. (99%)Dongshen Han; Sheng Zheng; Chaoning Zhang
IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks. (99%)Yue Cao; Tianlin Li; Xiaofeng Cao; Ivor Tsang; Yang Liu; Qing Guo
Revisiting Transferable Adversarial Image Examples: Attack Categorization, Evaluation Guidelines, and New Insights. (99%)Zhengyu Zhao; Hanwei Zhang; Renjue Li; Ronan Sicre; Laurent Amsaleg; Michael Backes; Qi Li; Chao Shen
Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm. (99%)S. M. Fazle Rabby Labib; Joyanta Jyoti Mondal; Meem Arafat Manab; Sarfaraz Newaz; Xi Xiao
Malicious Agent Detection for Robust Multi-Agent Collaborative Perception. (87%)Yangheng Zhao; Zhen Xiang; Sheng Yin; Xianghe Pang; Siheng Chen; Yanfeng Wang
Black-Box Training Data Identification in GANs via Detector Networks. (82%)Lukman Olagoke; Salil Vadhan; Seth Neel
Adversarial Training for Physics-Informed Neural Networks. (81%)Yao Li; Shengzhu Shi; Zhichang Guo; Boying Wu
REVAMP: Automated Simulations of Adversarial Attacks on Arbitrary Objects in Realistic Scenes. (80%)Matthew Hull; Zijie J. Wang; Duen Horng Chau
Quantifying Privacy Risks of Prompts in Visual Prompt Learning. (76%)Yixin Wu; Rui Wen; Michael Backes; Pascal Berrang; Mathias Humbert; Yun Shen; Yang Zhang
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now. (47%)Yimeng Zhang; Jinghan Jia; Xin Chen; Aochuan Chen; Yihua Zhang; Jiancheng Liu; Ke Ding; Sijia Liu
CAT: Closed-loop Adversarial Training for Safe End-to-End Driving. (2%)Linrui Zhang; Zhenghao Peng; Quanyi Li; Bolei Zhou
PrivInfer: Privacy-Preserving Inference for Black-box Large Language Model. (1%)Meng Tong; Kejiang Chen; Yuang Qi; Jie Zhang; Weiming Zhang; Nenghai Yu
2023-10-17
The Efficacy of Transformer-based Adversarial Attacks in Security Domains. (99%)Kunyang Li; Kyle Domico; Jean-Charles Noirot Ferrand; Patrick McDaniel
Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning. (93%)Taejin Kim; Jiarui Li; Shubhranshu Singh; Nikhil Madaan; Carlee Joe-Wong
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks. (15%)Jun Xia; Zhihao Yue; Yingbo Zhou; Zhiwei Ling; Xian Wei; Mingsong Chen
Generalizability of CNN Architectures for Face Morph Presentation Attack. (1%)Sherko R. HmaSalah; Aras Asaad
2023-10-16
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks. (98%)Erfan Shayegani; Md Abdullah Al Mamun; Yu Fu; Pedram Zaree; Yue Dong; Nael Abu-Ghazaleh
Regularization properties of adversarially-trained linear regression. (92%)Antônio H. Ribeiro; Dave Zachariah; Francis Bach; Thomas B. Schön
Fast Adversarial Label-Flipping Attack on Tabular Data. (84%)Xinglong Chang; Gillian Dobbie; Jörg Wicker
A Non-monotonic Smooth Activation Function. (83%)Koushik Biswas; Meghana Karri; Ulaş Bağcı
Quantifying Assistive Robustness Via the Natural-Adversarial Frontier. (68%)Jerry Zhi-Yang He; Zackory Erickson; Daniel S. Brown; Anca D. Dragan
A Comprehensive Study of Privacy Risks in Curriculum Learning. (67%)Joann Qiongna Chen; Xinlei He; Zheng Li; Yang Zhang; Zhou Li
DANAA: Towards transferable attacks with double adversarial neuron attribution. (26%)Zhibo Jin; Zhiyu Zhu; Xinyi Wang; Jiayu Zhang; Jun Shen; Huaming Chen
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective. (9%)Ganghua Wang; Xun Xian; Jayanth Srinivasa; Ashish Kundu; Xuan Bi; Mingyi Hong; Jie Ding
Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks. (4%)Shuyu Jiang; Xingshu Chen; Rui Tang
Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms. (3%)Alexander Bukharin; Yan Li; Yue Yu; Qingru Zhang; Zhehui Chen; Simiao Zuo; Chao Zhang; Songan Zhang; Tuo Zhao
Passive Inference Attacks on Split Learning via Adversarial Regularization. (3%)Xiaochen Zhu; Xinjian Luo; Yuncheng Wu; Yangfan Jiang; Xiaokui Xiao; Beng Chin Ooi
On the Transferability of Learning Models for Semantic Segmentation for Remote Sensing Data. (2%)Rongjun Qin; Guixiang Zhang; Yang Tang
Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning. (1%)Yanbiao Ma; Licheng Jiao; Fang Liu; Shuyuan Yang; Xu Liu; Lingling Li
Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts. (1%)Christina Chance; Da Yin; Dakuo Wang; Kai-Wei Chang
2023-10-15
Towards Deep Learning Models Resistant to Transfer-based Adversarial Attacks via Data-centric Robust Learning. (99%)Yulong Yang; Chenhao Lin; Xiang Ji; Qiwei Tian; Qian Li; Hongshan Yang; Zhibo Wang; Chao Shen
SCME: A Self-Contrastive Method for Data-free and Query-Limited Model Extraction Attack. (99%)Renyang Liu; Jinhong Zhang; Kwok-Yan Lam; Jun Zhao; Wei Zhou
AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings. (99%)Renyang Liu; Jinhong Zhang; Haoran Li; Jin Zhang; Yuanyu Wang; Wei Zhou
Black-box Targeted Adversarial Attack on Segment Anything (SAM). (99%)Sheng Zheng; Chaoning Zhang; Xinhong Hao
Evading Detection Actively: Toward Anti-Forensics against Forgery Localization. (97%)Long Zhuo; Shenghai Luo; Shunquan Tan; Han Chen; Bin Li; Jiwu Huang
Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attacks. (61%)Ziqiang Li; Pengfei Xia; Hong Sun; Yueqi Zeng; Wei Zhang; Bin Li
Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models? (9%)Yu-Lin Tsai; Chia-Yi Hsu; Chulin Xie; Chih-Hsun Lin; Jia-You Chen; Bo Li; Pin-Yu Chen; Chia-Mu Yu; Chun-Ying Huang
VFLAIR: A Research Library and Benchmark for Vertical Federated Learning. (3%)Tianyuan Zou; Zixuan Gu; Yu He; Hideaki Takahashi; Yang Liu; Ya-Qin Zhang
2023-10-14
BufferSearch: Generating Black-Box Adversarial Texts With Lower Queries. (98%)Wenjie Lv; Zhen Wang; Yitao Zheng; Zhehua Zhong; Qi Xuan; Tianyi Chen
2023-10-13
Is Certifying $\ell_p$ Robustness Still Worthwhile? (99%)Ravi Mangal; Klas Leino; Zifan Wang; Kai Hu; Weicheng Yu; Corina Pasareanu; Anupam Datta; Matt Fredrikson
User Inference Attacks on Large Language Models. (41%)Nikhil Kandpal; Krishna Pillutla; Alina Oprea; Peter Kairouz; Christopher A. Choquette-Choo; Zheng Xu
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting. (1%)Runqi Lin; Chaojian Yu; Bo Han; Tongliang Liu
2023-10-12
Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks. (99%)Giorgio Piras; Maura Pintor; Ambra Demontis; Battista Biggio
Concealed Electronic Countermeasures of Radar Signal with Adversarial Examples. (93%)Ruinan Ma; Canjie Zhu; Mingfeng Lu; Yunjie Li; Yu-an Tan; Ruibin Zhang; Ran Tao
Attacks Meet Interpretability (AmI) Evaluation and Findings. (92%)Qian Ma; Ziping Ye; Shagufta Mehnaz
Provably Robust Cost-Sensitive Learning via Randomized Smoothing. (73%)Yuan Xin; Michael Backes; Xiao Zhang
Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization. (68%)Giuseppe Floris; Raffaele Mura; Luca Scionis; Giorgio Piras; Maura Pintor; Ambra Demontis; Battista Biggio
Fed-Safe: Securing Federated Learning in Healthcare Against Adversarial Attacks. (64%)Erfan Darzi; Nanna M. Sijtsema; Ooijen P. M. A van
Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders. (31%)Jan Dubiński; Stanisław Pawlak; Franziska Boenisch; Tomasz Trzciński; Adam Dziedzic
Sentinel: An Aggregation Function to Secure Decentralized Federated Learning. (13%)Chao Feng; Alberto Huertas Celdran; Janosch Baltensperger; Enrique Tomas Matınez Bertran; Gerome Bovet; Burkhard Stiller
Defending Our Privacy With Backdoors. (10%)Dominik Hintersdorf; Lukas Struppek; Daniel Neider; Kristian Kersting
Investigating the Robustness and Properties of Detection Transformers (DETR) Toward Difficult Images. (9%)Zhao Ning Zou; Yuhang Zhang; Robert Wijaya
Polynomial Time Cryptanalytic Extraction of Neural Network Models. (3%)Adi Shamir; Isaac Canales-Martinez; Anna Hambitzer; Jorge Chavez-Saab; Francisco Rodrigez-Henriquez; Nitin Satpute
SEE-OoD: Supervised Exploration For Enhanced Out-of-Distribution Detection. (1%)Xiaoyang Song; Wenbo Sun; Maher Nouiehed; Raed Al Kontar; Judy Jin
XAI Benchmark for Visual Explanation. (1%)Yifei Zhang; Siyi Gu; James Song; Bo Pan; Liang Zhao
Jailbreaking Black Box Large Language Models in Twenty Queries. (1%)Patrick Chao; Alexander Robey; Edgar Dobriban; Hamed Hassani; George J. Pappas; Eric Wong
Voyager: MTD-Based Aggregation Protocol for Mitigating Poisoning Attacks on DFL. (1%)Chao Feng; Alberto Huertas Celdran; Michael Vuong; Gerome Bovet; Burkhard Stiller
2023-10-11
Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models. (99%)Renyang Liu; Wei Zhou; Tianwei Zhang; Kangjie Chen; Jun Zhao; Kwok-Yan Lam
Promoting Robustness of Randomized Smoothing: Two Cost-Effective Approaches. (89%)Linbo Liu; Trong Nghia Hoang; Lam M. Nguyen; Tsui-Wei Weng
An Adversarial Example for Direct Logit Attribution: Memory Management in gelu-4l. (13%)James Dao; Yeu-Tong Lao; Can Rager; Jett Janiak
Prompt Backdoors in Visual Prompt Learning. (11%)Hai Huang; Zhengyu Zhao; Michael Backes; Yun Shen; Yang Zhang
Why Train More? Effective and Efficient Membership Inference via Memorization. (10%)Jihye Choi; Shruti Tople; Varun Chandrasekaran; Somesh Jha
Towards Causal Deep Learning for Vulnerability Detection. (4%)Md Mahbubur Rahman; Ira Ceka; Chengzhi Mao; Saikat Chakraborty; Baishakhi Ray; Wei Le
Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey. (4%)Gregory Palmer; Chris Parry; Daniel J. B. Harrold; Chris Willis
2023-10-10
A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks. (99%)Yang Wang; Bo Dong; Ke Xu; Haiyin Piao; Yufei Ding; Baocai Yin; Xin Yang
My Brother Helps Me: Node Injection Based Adversarial Attack on Social Bot Detection. (98%)Lanjun Wang; Xinran Qiao; Yanwei Xie; Weizhi Nie; Yongdong Zhang; Anan Liu
Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach. (83%)Kai Zhao; Qiyu Kang; Yang Song; Rui She; Sijie Wang; Wee Peng Tay
Adversarial optimization leads to over-optimistic security-constrained dispatch, but sampling can help. (76%)Charles Dawson; Chuchu Fan
No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML. (62%)Ziqi Zhang; Chen Gong; Yifeng Cai; Yuanyuan Yuan; Bingyan Liu; Ding Li; Yao Guo; Xiangqun Chen
Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks. (47%)Anastasia Antsiferova; Khaled Abud; Aleksandr Gushchin; Ekaterina Shumitskaya; Sergey Lavrushkin; Dmitriy Vatolin
GraphCloak: Safeguarding Task-specific Knowledge within Graph-structured Data from Unauthorized Exploitation. (22%)Yixin Liu; Chenrui Fan; Xun Chen; Pan Zhou; Lichao Sun
Latent Diffusion Counterfactual Explanations. (5%)Karim Farid; Simon Schrodi; Max Argus; Thomas Brox
FTFT: efficient and robust Fine-Tuning by transFerring Training dynamics. (2%)Yupei Du; Albert Gatt; Dong Nguyen
Investigating the Adversarial Robustness of Density Estimation Using the Probability Flow ODE. (2%)Marius Arvinte; Cory Cornelius; Jason Martin; Nageen Himayat
Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations. (1%)Zeming Wei; Yifei Wang; Yisen Wang
2023-10-09
PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization. (92%)Jiancong Xiao; Ruoyu Sun; Zhi- Quan Luo
Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand. (22%)Junfeng Guo; Yiming Li; Lixu Wang; Shu-Tao Xia; Heng Huang; Cong Liu; Bo Li
Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach. (5%)Shaopeng Fu; Di Wang
Exploring adversarial attacks in federated learning for medical imaging. (2%)Erfan Darzi; Florian Dubost; N. M. Sijtsema; Ooijen P. M. A van
2023-10-08
GReAT: A Graph Regularized Adversarial Training Method. (99%)Samet Bayram; Kenneth Barner
An Initial Investigation of Neural Replay Simulator for Over-the-Air Adversarial Perturbations to Automatic Speaker Verification. (99%)Jiaqi Li; Li Wang; Liumeng Xue; Lei Wang; Zhizheng Wu
AdvSV: An Over-the-Air Adversarial Attack Dataset for Speaker Verification. (96%)Li Wang; Jiaqi Li; Yuhao Luo; Jiahao Zheng; Lei Wang; Hao Li; Ke Xu; Chengfang Fang; Jie Shi; Zhizheng Wu
Transferable Availability Poisoning Attacks. (83%)Yiyong Liu; Michael Backes; Xiao Zhang
BRAINTEASER: Lateral Thinking Puzzles for Large Language Models. (26%)Yifan Jiang; Filip Ilievski; Kaixin Ma; Zhivar Sourati
Stealthy Backdoor Attack via Confidence-driven Sampling. (10%)Pengfei He; Yue Xing; Han Xu; Jie Ren; Yingqian Cui; Shenglai Zeng; Jiliang Tang; Makoto Yamada; Mohammad Sabokrou
Adversarial Attacks on Combinatorial Multi-Armed Bandits. (5%)Rishab Balasubramanian; Jiawei Li; Prasad Tadepalli; Huazheng Wang; Qingyun Wu; Haoyu Zhao
2023-10-07
Improving Adversarial Attacks on Latent Diffusion Model. (99%)Boyang Zheng; Chumeng Liang; Xiaoyu Wu; Yan Liu
IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers. (76%)Zhenglin Huang; Xiaoan Bao; Na Zhang; Qingqi Zhang; Xiaomei Tu; Biao Wu; Xi Yang
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line. (1%)Eungyeup Kim; Mingjie Sun; Christina Baek; Aditi Raghunathan; J. Zico Kolter
2023-10-06
VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models. (98%)Ziyi Yin; Muchao Ye; Tianrong Zhang; Tianyu Du; Jinguo Zhu; Han Liu; Jinghui Chen; Ting Wang; Fenglong Ma
Generating Less Certain Adversarial Examples Improves Robust Generalization. (98%)Minxing Zhang; Michael Backes; Xiao Zhang
Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification. (84%)Shanshan Han; Wenxuan Wu; Baturalp Buyukates; Weizhao Jin; Qifan Zhang; Yuhang Yao; Salman Avestimehr; Chaoyang He
2023-10-05
OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks. (99%)Ofir Bar Tal; Adi Haviv; Amit H. Bermano
Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System. (99%)Khushnaseeb Roshan; Aasim Zafar; Sheikh Burhan Ul Haque
Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria. (99%)Nuoyan Zhou; Nannan Wang; Decheng Liu; Dawei Zhou; Xinbo Gao
An Integrated Algorithm for Robust and Imperceptible Audio Adversarial Examples. (98%)Armin Ettenhofer; Jan-Philipp Schulze; Karla Pizzi
Adversarial Machine Learning for Social Good: Reframing the Adversary as an Ally. (98%)Shawqi Al-Maliki; Adnan Qayyum; Hassan Ali; Mohamed Abdallah; Junaid Qadir; Dinh Thai Hoang; Dusit Niyato; Ala Al-Fuqaha
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks. (92%)Alexander Robey; Eric Wong; Hamed Hassani; George J. Pappas
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks. (64%)Wenhan Yang; Jingdong Gao; Baharan Mirzasoleiman
Targeted Adversarial Attacks on Generalizable Neural Radiance Fields. (56%)Andras Horvath; Csaba M. Jozsa
Certification of Deep Learning Models for Medical Image Segmentation. (15%)Othmane Laousy; Alexandre Araujo; Guillaume Chassagnon; Nikos Paragios; Marie-Pierre Revel; Maria Vakalopoulou
Certifiably Robust Graph Contrastive Learning. (5%)Minhua Lin; Teng Xiao; Enyan Dai; Xiang Zhang; Suhang Wang
Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations. (2%)Jiachi Liu; Liwen Wang; Guanting Dong; Xiaoshuai Song; Zechen Wang; Zhengyang Wang; Shanglin Lei; Jinzheng Zhao; Keqing He; Bo Xiao; Weiran Xu
2023-10-04
Optimizing Key-Selection for Face-based One-Time Biometrics via Morphing. (98%)Daile Osorio-Roig; Mahdi Ghafourian; Christian Rathgeb; Ruben Vera-Rodriguez; Christoph Busch; Julian Fierrez
Misusing Tools in Large Language Models With Visual Adversarial Examples. (97%)Xiaohan Fu; Zihan Wang; Shuheng Li; Rajesh K. Gupta; Niloofar Mireshghallah; Taylor Berg-Kirkpatrick; Earlence Fernandes
Burning the Adversarial Bridges: Robust Windows Malware Detection Against Binary-level Mutations. (82%)Ahmed Abusnaina; Yizhen Wang; Sunpreet Arora; Ke Wang; Mihai Christodorescu; David Mohaisen
Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors. (81%)Biagio Montaruli; Luca Demetrio; Maura Pintor; Luca Compagna; Davide Balzarotti; Battista Biggio
Shielding the Unseen: Privacy Protection through Poisoning NeRF with Spatial Deformation. (10%)Yihan Wu; Brandon Y. Feng; Heng Huang
2023-10-03
Splitting the Difference on Adversarial Training. (99%)Matan Levi; Aryeh Kontorovich
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training. (97%)Aochuan Chen; Yimeng Zhang; Jinghan Jia; James Diffenderfer; Jiancheng Liu; Konstantinos Parasyris; Yihua Zhang; Zheng Zhang; Bhavya Kailkhura; Sijia Liu
SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers. (86%)KL Navaneet; Soroush Abbasi Koohpayegani; Essam Sleiman; Hamed Pirsiavash
Towards Stable Backdoor Purification through Feature Shift Tuning. (83%)Rui Min; Zeyu Qin; Li Shen; Minhao Cheng
Jailbreaker in Jail: Moving Target Defense for Large Language Models. (73%)Bocheng Chen; Advait Paliwal; Qiben Yan
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models. (56%)Xiaogeng Liu; Nan Xu; Muhao Chen; Chaowei Xiao
Beyond Labeling Oracles: What does it mean to steal ML models? (47%)Avital Shafran; Ilia Shumailov; Murat A. Erdogdu; Nicolas Papernot
A Recipe for Improved Certifiable Robustness. (22%)Kai Hu; Klas Leino; Zifan Wang; Matt Fredrikson
Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness. (13%)Yanzhao Wu; Ka-Ho Chow; Wenqi Wei; Ling Liu
FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attacks. (11%)Jorge Castillo; Phillip Rieger; Hossein Fereidooni; Qian Chen; Ahmad Sadeghi
AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Framework. (3%)Xilie Xu; Jingfeng Zhang; Mohan Kankanhalli
2023-10-02
Fooling the Textual Fooler via Randomizing Latent Representations. (99%)Duy C. Hoang; Quang H. Nguyen; Saurav Manchanda; MinLong Peng; Kok-Seng Wong; Khoa D. Doan
LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples. (93%)Jia-Yu Yao; Kun-Peng Ning; Zhen-Hui Liu; Mu-Nan Ning; Li Yuan
Adversarial Client Detection via Non-parametric Subspace Monitoring in the Internet of Federated Things. (92%)Xianjian Xie; Xiaochen Xian; Dan Li; Andi Wang
LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model. (87%)Muhammad Ahmed Shah; Roshan Sharma; Hira Dhamyal; Raphael Olivier; Ankit Shah; Joseph Konan; Dareen Alharthi; Hazim T Bukhari; Massa Baali; Soham Deshmukh; Michael Kuhlmann; Bhiksha Raj; Rita Singh
Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models. (13%)Zhou Yang; Zhipeng Zhao; Chenyu Wang; Jieke Shi; Dongsum Kim; Donggyun Han; David Lo
Toward effective protection against diffusion based mimicry through score distillation. (3%)Haotian Xue; Chumeng Liang; Xiaoyu Wu; Yongxin Chen
Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations. (1%)Yongshuo Zong; Tingyang Yu; Bingchen Zhao; Ruchika Chavhan; Timothy Hospedales
2023-10-01
A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attacks. (99%)Yanjie Li; Bin Xie; Songtao Guo; Yuanyuan Yang; Bin Xiao
Counterfactual Image Generation for adversarially robust and interpretable Classifiers. (96%)Rafael Bischof; Florian Scheidegger; Michael A. Kraus; A. Cristiano I. Malossi
Understanding Adversarial Transferability in Federated Learning. (93%)Yijiang Li; Ying Gao; Haohan Wang
On the Onset of Robust Overfitting in Adversarial Training. (87%)Chaojian Yu; Xiaolong Shi; Jun Yu; Bo Han; Tongliang Liu
GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning. (61%)Qiannan Wang; Changchun Yin; Zhe Liu; Liming Fang; Run Wang; Chenhao Lin
Fewer is More: Trojan Attacks on Parameter-Efficient Fine-Tuning. (9%)Lauren Hong; Ting Wang
Can Pre-trained Networks Detect Familiar Out-of-Distribution Data? (1%)Atsuyuki Miyai; Qing Yu; Go Irie; Kiyoharu Aizawa
How well does LLM generate security tests? (1%)Ying Daphne Zhang; Wenjia Daphne Song; Zhengjie Daphne Ji; Daphne Danfeng; Yao; Na Meng
2023-09-30
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks. (99%)Quang H. Nguyen; Yingjie Lao; Tung Pham; Kok-Seng Wong; Khoa D. Doan
Human-Producible Adversarial Examples. (98%)David Khachaturov; Yue Gao; Ilia Shumailov; Robert Mullins; Ross Anderson; Kassem Fawaz
Black-box Attacks on Image Activity Prediction and its Natural Language Explanations. (98%)Alina Elena Baia; Valentina Poggioni; Andrea Cavallaro
Horizontal Class Backdoor to Deep Learning. (84%)Hua Ma; Shang Wang; Yansong Gao
Refutation of Shapley Values for XAI -- Additional Evidence. (8%)Xuanxiang Huang; Joao Marques-Silva
2023-09-29
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks. (99%)Mehrdad Saberi; Vinu Sankar Sadasivan; Keivan Rezaei; Aounon Kumar; Atoosa Chegini; Wenxiao Wang; Soheil Feizi
Efficient Biologically Plausible Adversarial Training. (98%)Matilde Tristany Farinha; Thomas Ortner; Giorgia Dellaferrera; Benjamin Grewe; Angeliki Pantazi
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks. (96%)Vaidehi Patil; Peter Hase; Mohit Bansal
On Continuity of Robust and Accurate Classifiers. (93%)Ramin Barati; Reza Safabakhsh; Mohammad Rahmati
Adversarial Machine Learning in Latent Representations of Neural Networks. (93%)Milin Zhang; Mohammad Abdi; Francesco Restuccia
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization. (92%)Mahyar Fazlyab; Taha Entesari; Aniket Roy; Rama Chellappa
Toward Robust Recommendation via Real-time Vicinal Defense. (82%)Yichang Xu; Chenwang Wu; Defu Lian
Adversarial Explainability: Utilizing Explainable Machine Learning in Bypassing IoT Botnet Detection Systems. (31%)Mohammed M. Alani; Atefeh Mashatan; Ali Miri
Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study. (13%)Myeongseob Ko; Ming Jin; Chenguang Wang; Ruoxi Jia
Distributed Resilient Control of DC Microgrids Under Generally Unbounded FDI Attacks. (1%)Yichao Wang; Mohamadamin Rajabinezhad; Omar A. Beg; Shan Zuo
Source Inference Attacks: Beyond Membership Inference Attacks in Federated Learning. (1%)Hongsheng Hu; Xuyun Zhang; Zoran Salcic; Lichao Sun; Kim-Kwang Raymond Choo; Gillian Dobbie
2023-09-28
Investigating Human-Identifiable Features Hidden in Adversarial Perturbations. (98%)Dennis Y. Menn; Tzu-hsun Feng; Sriram Vishwanath; Hung-yi Lee
Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworks. (98%)Huihui Gong; Minjing Dong; Siqi Ma; Seyit Camtepe; Surya Nepal; Chang Xu
Towards Poisoning Fair Representations. (70%)Tianci Liu; Haoyu Wang; Feijie Wu; Hengtong Zhang; Pan Li; Lu Su; Jing Gao
On the Trade-offs between Adversarial Robustness and Actionable Explanations. (68%)Satyapriya Krishna; Chirag Agarwal; Himabindu Lakkaraju
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing. (56%)Blaise Delattre; Alexandre Araujo; Quentin Barthélemy; Alexandre Allauzen
Post-Training Overfitting Mitigation in DNN Classifiers. (41%)Hang Wang; David J. Miller; George Kesidis
Leveraging Optimization for Adaptive Attacks on Image Watermarks. (13%)Nils Lukas; Abdulrahman Diaa; Lucas Fenaux; Florian Kerschbaum
Random and Safe Cache Architecture to Defeat Cache Timing Attacks. (9%)Guangyuan Hu; Ruby B. Lee
Robust Offline Reinforcement Learning -- Certify the Confidence Interval. (4%)Jiarui Yao; Simon Shaolei Du
A Primer on Bayesian Neural Networks: Review and Debates. (2%)Julyan Arbel; Konstantinos Pitas; Mariia Vladimirova; Vincent Fortuin
2023-09-27
On the Computational Entanglement of Distant Features in Adversarial Machine Learning. (99%)YenLung Lai; Xingbo Dong; Zhe Jin
Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness. (95%)Ambar Pal; Jeremias Sulam; René Vidal
Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection. (95%)Lukas Strack; Futa Waseda; Huy H. Nguyen; Yinqiang Zheng; Isao Echizen
Automatic Feature Fairness in Recommendation via Adversaries. (33%)Hengchang Hu; Yiming Cao; Zhankui He; Samson Tan; Min-Yen Kan
Warfare:Breaking the Watermark Protection of AI-Generated Content. (12%)Guanlin Li; Yifei Chen; Jie Zhang; Jiwei Li; Shangwei Guo; Tianwei Zhang
Generating Transferable Adversarial Simulation Scenarios for Self-Driving via Neural Rendering. (11%)Yasasa Abeysirigoonawardena; Kevin Xie; Chuhan Chen; Salar Hosseini; Ruiting Chen; Ruiqi Wang; Florian Shkurti
Breaking On-Chip Communication Anonymity using Flow Correlation Attacks. (4%)Hansika Weerasena; Prabhat Mishra
Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic Classification. (1%)Mahmoud Nazzal; Nura Aljaafari; Ahmed Sawalmeh; Abdallah Khreishah; Muhammad Anan; Abdulelah Algosaibi; Mohammed Alnaeem; Adel Aldalbahi; Abdulaziz Alhumam; Conrado P. Vizcarra; Shadan Alhamed
2023-09-26
Structure Invariant Transformation for better Adversarial Transferability. (99%)Xiaosen Wang; Zeliang Zhang; Jianping Zhang
Privacy-preserving and Privacy-attacking Approaches for Speech and Audio -- A Survey. (16%)Yuchen Liu; Apu Kapadia; Donald Williamson
Neural Stochastic Differential Equations for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions. (2%)Sumit Kumar Jha; Susmit Jha; Rickard Ewetz; Alvaro Velasquez
Collaborative Watermarking for Adversarial Speech Synthesis. (1%)Lauri Aalto University, Finland Juvela; Xin National Institute of Informatics, Japan Wang
2023-09-25
DifAttack: Query-Efficient Black-Box Attack via Disentangled Feature Space. (99%)Liu Jun; Zhou Jiantao; Zeng Jiandian; Jinyu Tian
Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents. (98%)Foozhan Ataiefard; Hadi Hemmati
SurrogatePrompt: Bypassing the Safety Filter of Text-To-Image Models via Substitution. (1%)Zhongjie Ba; Jieming Zhong; Jiachen Lei; Peng Cheng; Qinglong Wang; Zhan Qin; Zhibo Wang; Kui Ren
2023-09-24
Adversarial Attacks on Video Object Segmentation with Hard Region Discovery. (99%)Ping Li; Yu Zhang; Li Yuan; Jian Zhao; Xianghua Xu; Xiaoqin Zhang
Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks. (98%)Ao-Xiang Zhang; Yu Ran; Weixuan Tang; Yuan-Gen Wang
On the Effectiveness of Adversarial Samples against Ensemble Learning-based Windows PE Malware Detectors. (86%)Trong-Nghia To; Danh Le Kim; Do Thi Thu Hien; Nghi Hoang Khoa; Hien Do Hoang; Phan The Duy; Van-Hau Pham
Benchmarking Local Robustness of High-Accuracy Binary Neural Networks for Enhanced Traffic Sign Recognition. (80%)Andreea Postovan; Mădălina Eraşcu
Projected Randomized Smoothing for Certified Adversarial Robustness. (76%)Samuel Pfrommer; Brendon G. Anderson; Somayeh Sojoudi
Combining Two Adversarial Attacks Against Person Re-Identification Systems. (73%)Eduardo de O. Andrade; Igor Garcia Ballhausen Sampaio; Joris Guérin; José Viterbo
Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models. (2%)Minghang Deng; Zhong Zhang; Junming Shao
2023-09-23
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks. (61%)Zhaohan Xi; Tianyu Du; Changjiang Li; Ren Pang; Shouling Ji; Jinghui Chen; Fenglong Ma; Ting Wang
Moving Target Defense based Secured Network Slicing System in the O-RAN Architecture. (1%)Mojdeh Karbalaee Motalleb; Chafika Benzaïd; Tarik Taleb; Vahid Shah-Mansouri
Detecting and Mitigating System-Level Anomalies of Vision-Based Controllers. (1%)Aryaman Gupta; Kaustav Chakraborty; Somil Bansal
2023-09-22
RBFormer: Improve Adversarial Robustness of Transformer by Robust Bias. (99%)Hao Cheng; Jinhao Duan; Hui Li; Lyutianyang Zhang; Jiahang Cao; Ping Wang; Jize Zhang; Kaidi Xu; Renjing Xu
Spatial-frequency channels, shape bias, and adversarial robustness. (69%)Ajay Subramanian; Elena Sizikova; Najib J. Majaj; Denis G. Pelli
VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks. (69%)Heitor R. Guimarães; Arthur Pimentel; Anderson Avila; Tiago H. Falk
Understanding Deep Gradient Leakage via Inversion Influence Functions. (15%)Haobo Zhang; Junyuan Hong; Yuyang Deng; Mehrdad Mahdavi; Jiayu Zhou
Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations. (10%)Hanjiang Hu; Zuxin Liu; Linyi Li; Jiacheng Zhu; Ding Zhao
Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception? (5%)Xiaoxiao Sun; Nidham Gazagnadou; Vivek Sharma; Lingjuan Lyu; Hongdong Li; Liang Zheng
Expressive variational quantum circuits provide inherent privacy in federated learning. (1%)Niraj Kumar; Jamie Heredge; Changhao Li; Shaltiel Eloul; Shree Hari Sureshbabu; Marco Pistoia
On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasures. (1%)Qingzhao Zhang; Shuowei Jin; Ruiyang Zhu; Jiachen Sun; Xumiao Zhang; Qi Alfred Chen; Z. Morley Mao
2023-09-21
Improving Machine Learning Robustness via Adversarial Training. (99%)Long Dang; Thushari Hapuarachchi; Kaiqi Xiong; Jing Lin
Goal-Oriented Prompt Attack and Safety Evaluation for LLMs. (69%)Chengyuan Liu; Fubang Zhao; Lizhi Qing; Yangyang Kang; Changlong Sun; Kun Kuang; Fei Wu
HANS, are you clever? Clever Hans Effect Analysis of Neural Systems. (45%)Leonardo Ranaldi; Fabio Massimo Zanzotto
On the Relationship between Skill Neurons and Robustness in Prompt Tuning. (12%)Leon Ackermann; Xenia Ohmer
DeepTheft: Stealing DNN Model Architectures through Power Side Channel. (1%)Yansong Gao; Huming Qiu; Zhi Zhang; Binghui Wang; Hua Ma; Alsharif Abuadbba; Minhui Xue; Anmin Fu; Surya Nepal
2023-09-20
How Robust is Google's Bard to Adversarial Image Attacks? (99%)Yinpeng Dong; Huanran Chen; Jiawei Chen; Zhengwei Fang; Xiao Yang; Yichi Zhang; Yu Tian; Hang Su; Jun Zhu
PRAT: PRofiling Adversarial aTtacks. (99%)Rahul Ambati; Naveed Akhtar; Ajmal Mian; Yogesh Singh Rawat
When to Trust AI: Advances and Challenges for Certification of Neural Networks. (64%)Marta Kwiatkowska; Xiyue Zhang
AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition. (54%)Mohamad Fakih; Rouwaida Kanj; Fadi Kurdahi; Mohammed E. Fouda
Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation. (54%)Krishna Kanth Nakka; Mathieu Salzmann
Fed-LSAE: Thwarting Poisoning Attacks against Federated Cyber Threat Detection System via Autoencoder-based Latent Space Inspection. (5%)Tran Duc Luong; Vuong Minh Tien; Nguyen Huu Quyen; Do Thi Thu Hien; Phan The Duy; Van-Hau Pham
Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization. (2%)Stefan Trawicki; William Hackett; Lewis Birch; Neeraj Suri; Peter Garraghan
Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer. (1%)Anwei Luo; Rizhao Cai; Chenqi Kong; Yakun Ju; Xiangui Kang; Jiwu Huang; Alex C. Kot
2023-09-19
Language Guided Adversarial Purification. (99%)Himanshu Singh; A V Subramanyam
What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples. (99%)Shakila Mahjabin Tonni; Mark Dras
Adversarial Attacks Against Uncertainty Quantification. (99%)Emanuele Ledda; Daniele Angioni; Giorgio Piras; Giorgio Fumera; Battista Biggio; Fabio Roli
Model Leeching: An Extraction Attack Targeting LLMs. (76%)Lewis Birch; William Hackett; Stefan Trawicki; Neeraj Suri; Peter Garraghan
Information Leakage from Data Updates in Machine Learning Models. (16%)Tian Hui; Farhad Farokhi; Olga Ohrimenko
Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers. (16%)Zhen Li; Ruqian Zhang; Deqing Zou; Ning Wang; Yating Li; Shouhuai Xu; Chen Chen; Hai Jin
SPFL: A Self-purified Federated Learning Method Against Poisoning Attacks. (12%)Zizhen Liu; Weiyang He; Chip-Hong Chang; Jing Ye; Huawei Li; Xiaowei Li
It's Simplex! Disaggregating Measures to Improve Certified Robustness. (11%)Andrew C. Cullen; Paul Montague; Shijie Liu; Sarah M. Erfani; Benjamin I. P. Rubinstein
Nebula: Self-Attention for Dynamic Malware Analysis. (5%)Dmitrijs Trizna; Luca Demetrio; Battista Biggio; Fabio Roli
Extreme Image Transformations Facilitate Robust Latent Object Representations. (1%)Girik Malik; Dakarai Crowder; Ennio Mingolla
2023-09-18
Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization. (99%)Huihui Gong; Minjing Dong; Siqi Ma; Seyit Camtepe; Surya Nepal; Chang Xu
Transferable Adversarial Attack on Image Tampering Localization. (99%)Yuqi Wang; Gang Cao; Zijie Lou; Haochen Zhu
Efficient Low-Rank GNN Defense Against Structural Attacks. (96%)Abdullah Alchihabi; Qing En; Yuhong Guo
Evaluating Adversarial Robustness with Expected Viable Performance. (45%)Ryan McCoppin; Colin Dawson; Sean M. Kennedy; Leslie M. Blaha
Dual Student Networks for Data-Free Model Stealing. (26%)James Beetham; Navid Kardan; Ajmal Mian; Mubarak Shah
Securing Fixed Neural Network Steganography. (5%)Zicong Luo; Sheng Li; Guobiao Li; Zhenxing Qian; Xinpeng Zhang
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts. (4%)Jiahao Yu; Xingwei Lin; Zheng Yu; Xinyu Xing
Spoofing attack augmentation: can differently-trained attack models improve generalisation? (3%)Wanying Ge; Xin Wang; Junichi Yamagishi; Massimiliano Todisco; Nicholas Evans
Frame-to-Utterance Convergence: A Spectra-Temporal Approach for Unified Spoofing Detection. (1%)Awais Khan; Khalid Mahmood Malik; Shah Nawaz
2023-09-17
Reducing Adversarial Training Cost with Gradient Approximation. (99%)Huihui Gong; Shuo Yang; Siqi Ma; Seyit Camtepe; Surya Nepal; Chang Xu
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM. (61%)Bochuan Cao; Yuanpu Cao; Lu Lin; Jinghui Chen
2023-09-16
Context-aware Adversarial Attack on Named Entity Recognition. (99%)Shuguang Chen; Leonardo Neves; Thamar Solorio
Inverse classification with logistic and softmax classifiers: efficient optimization. (56%)Miguel Á. Carreira-Perpiñán; Suryabhan Singh Hada
Robust Backdoor Attacks on Object Detection in Real World. (11%)Yaguan Qian; Boyuan Ji; Shuke He; Shenhui Huang; Xiang Ling; Bin Wang; Wei Wang
Conditional Mutual Information Constrained Deep Learning for Classification. (5%)En-Hui Yang; Shayan Mohajer Hamidi; Linfeng Ye; Renhao Tan; Beverly Yang
2023-09-15
Adversarial Attacks on Tables with Entity Swap. (92%)Aneta Koleva; Martin Ringsquandl; Volker Tresp
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks. (87%)Minh-Hao Van; Alycia N. Carey; Xintao Wu
Distributionally Robust Post-hoc Classifiers under Prior Shifts. (1%)Jiaheng Wei; Harikrishna Narasimhan; Ehsan Amid; Wen-Sheng Chu; Yang Liu; Abhishek Kumar
A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services. (1%)Hongsheng Hu; Shuo Wang; Jiamin Chang; Haonan Zhong; Ruoxi Sun; Shuang Hao; Haojin Zhu; Minhui Xue
2023-09-14
Unleashing the Adversarial Facet of Software Debloating. (98%)Do-Men Su; Mohannad Alhanahnah
SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems. (76%)Guangke Chen; Yedi Zhang; Fu Song
What Matters to Enhance Traffic Rule Compliance of Imitation Learning for Automated Driving. (50%)Hongkuan Zhou; Aifen Sui; Wei Cao; Zhenshan Bing
BAGEL: Backdoor Attacks against Federated Contrastive Learning. (16%)Yao Huang; Kongyang Chen; Jiannong Cao; Jiaxing Shen; Shaowei Wang; Yun Peng; Weilong Peng; Kechao Cai
Physical Invisible Backdoor Based on Camera Imaging. (2%)Yusheng Guo; Nan Zhong; Zhenxing Qian; Xinpeng Zhang
M3Dsynth: A dataset of medical 3D images with AI-generated local manipulations. (1%)Giada Zingarini; Davide Cozzolino; Riccardo Corvi; Giovanni Poggi; Luisa Verdoliva
2023-09-13
Semantic Adversarial Attacks via Diffusion Models. (99%)Chenan Wang; Jinhao Duan; Chaowei Xiao; Edward Kim; Matthew Stamm; Kaidi Xu
Hardening RGB-D Object Recognition Systems against Adversarial Patch Attacks. (99%)Yang Zheng; Luca Demetrio; Antonio Emanuele Cinà; Xiaoyi Feng; Zhaoqiang Xia; Xiaoyue Jiang; Ambra Demontis; Battista Biggio; Fabio Roli
Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments. (99%)Simon Queyrut; Valerio Schiavoni; Pascal Felber
PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection. (99%)Hanqing Guo; Guangjing Wang; Yuanda Wang; Bocheng Chen; Qiben Yan; Li Xiao
APICom: Automatic API Completion via Prompt Learning and Adversarial Training-based Data Augmentation. (92%)Yafeng Gu; Yiheng Shen; Xiang Chen; Shaoyu Yang; Yiling Huang; Zhixiang Cao
RAIN: Your Language Models Can Align Themselves without Finetuning. (83%)Yuhui Li; Fangyun Wei; Jinjing Zhao; Chao Zhang; Hongyang Zhang
Differentiable JPEG: The Devil is in the Details. (70%)Christoph Reich; Biplob Debnath; Deep Patel; Srimat Chakradhar
Deep Nonparametric Convexified Filtering for Computational Photography, Image Synthesis and Adversarial Defense. (41%)Jianqiao Wangni
MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems. (38%)Hanqing Guo; Xun Chen; Junfeng Guo; Li Xiao; Qiben Yan
Client-side Gradient Inversion Against Federated Learning from Poisoning. (22%)Jiaheng Wei; Yanjun Zhang; Leo Yu Zhang; Chao Chen; Shirui Pan; Kok-Leong Ong; Jun Zhang; Yang Xiang
Safe Reinforcement Learning with Dual Robustness. (1%)Zeyang Li; Chuxiong Hu; Yunan Wang; Yujie Yang; Shengbo Eben Li
2023-09-12
Using Reed-Muller Codes for Classification with Rejection and Recovery. (99%)Daniel University of Birmingham Fentham; David University of Oxford Parker; Mark University of Birmingham Ryan
Certified Robust Models with Slack Control and Large Lipschitz Constants. (98%)Max Losch; David Stutz; Bernt Schiele; Mario Fritz
Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks. (98%)Jindong Gu; Fangyun Wei; Philip Torr; Han Hu
Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables. (83%)Yanzuo The Hong Kong University of Science and Technology Chen; Zhibo The Hong Kong University of Science and Technology Liu; Yuanyuan The Hong Kong University of Science and Technology Yuan; Sihang Huawei Technologies Hu; Tianxiang Huawei Technologies Li; Shuai The Hong Kong University of Science and Technology Wang
Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review. (61%)Pengzhou Cheng; Zongru Wu; Wei Du; Gongshen Liu
CToMP: A Cycle-task-oriented Memory Protection Scheme for Unmanned Systems. (8%)Chengyan Ma; Ning Xi; Di Lu; Yebo Feng; Jianfeng Ma
Language Models as Black-Box Optimizers for Vision-Language Models. (4%)Shihong Liu; Zhiqiu Lin; Samuel Yu; Ryan Lee; Tiffany Ling; Deepak Pathak; Deva Ramanan
2023-09-11
Generalized Attacks on Face Verification Systems. (88%)Ehsan Nazari; Paula Branco; Guy-Vincent Jourdan
Adversarial Attacks Assessment of Salient Object Detection via Symbolic Learning. (76%)Gustavo Olague; Roberto Pineda; Gerardo Ibarra-Vazquez; Matthieu Olague; Axel Martinez; Sambit Bakshi; Jonathan Vargas; Isnardo Reducindo
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System. (68%)Peixin Zhang; Jun Sun; Mingtian Tan; Xinyu Wang
Privacy Side Channels in Machine Learning Systems. (10%)Edoardo Debenedetti; Giorgio Severi; Nicholas Carlini; Christopher A. Choquette-Choo; Matthew Jagielski; Milad Nasr; Eric Wallace; Florian Tramèr
Divergences in Color Perception between Deep Neural Networks and Humans. (4%)Ethan O. Nadler; Elise Darragh-Ford; Bhargav Srinivasa Desikan; Christian Conaway; Mark Chu; Tasker Hull; Douglas Guilbeault
Catch You Everything Everywhere: Guarding Textual Inversion via Concept Watermarking. (1%)Weitao Feng; Jiyan He; Jie Zhang; Tianwei Zhang; Wenbo Zhou; Weiming Zhang; Nenghai Yu
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs. (1%)Wenhua Cheng; Weiwei Zhang; Haihao Shen; Yiyang Cai; Xin He; Kaokao Lv
2023-09-10
Outlier Robust Adversarial Training. (98%)Shu Hu; Zhenhuan Yang; Xin Wang; Yiming Ying; Siwei Lyu
DAD++: Improved Data-free Test Time Adversarial Defense. (98%)Gaurav Kumar Nayak; Inder Khatri; Shubham Randive; Ruchit Rawal; Anirban Chakraborty
Machine Translation Models Stand Strong in the Face of Adversarial Attacks. (86%)Pavel Burnyshev; Elizaveta Kostenok; Alexey Zaytsev
Secure Set-Based State Estimation for Linear Systems under Adversarial Attacks on Sensors. (12%)M. Umar B. Niazi; Michelle S. Chong; Amr Alanwar; Karl H. Johansson
2023-09-09
Towards Robust Model Watermark via Reducing Parametric Vulnerability. (8%)Guanhao Gan; Yiming Li; Dongxian Wu; Shu-Tao Xia
RecAD: Towards A Unified Library for Recommender Attack and Defense. (1%)Changsheng Wang; Jianbai Ye; Wenjie Wang; Chongming Gao; Fuli Feng; Xiangnan He
2023-09-08
Exploring Robust Features for Improving Adversarial Robustness. (99%)Hong Wang; Yuefan Deng; Shinjae Yoo; Yuewei Lin
ARRTOC: Adversarially Robust Real-Time Optimization and Control. (2%)Akhil Ahmed; Rio-Chanona Ehecatl Antonio del; Mehmet Mercangoz
Adversarial attacks on hybrid classical-quantum Deep Learning models for Histopathological Cancer Detection. (1%)Biswaraj Baral; Reek Majumdar; Bhavika Bhalgamiya; Taposh Dutta Roy
Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse. (1%)Edward A. Small; Jeffrey N. Clark; Christopher J. McWilliams; Kacper Sokol; Jeffrey Chan; Flora D. Salim; Raul Santos-Rodriguez
2023-09-07
Experimental Study of Adversarial Attacks on ML-based xApps in O-RAN. (99%)Naveen Naik Sapavath; Brian Kim; Kaushik Chowdhury; Vijay K Shah
How adversarial attacks can disrupt seemingly stable accurate classifiers. (99%)Oliver J. Sutton; Qinghua Zhou; Ivan Y. Tyukin; Alexander N. Gorban; Alexander Bastounis; Desmond J. Higham
Adversarially Robust Deep Learning with Optimal-Transport-Regularized Divergences. (95%)Jeremiah Birrell; Mohammadreza Ebrahimi
DiffDefense: Defending against Adversarial Attacks via Diffusion Models. (80%)Hondamunige Prasanna Silva; Lorenzo Seidenari; Bimbo Alberto Del
One-to-Multiple Clean-Label Image Camouflage (OmClic) based Backdoor Attack on Deep Learning. (73%)Guohong Wang; Hua Ma; Yansong Gao; Alsharif Abuadbba; Zhi Zhang; Wei Kang; Said F. Al-Sarawib; Gongxuan Zhang; Derek Abbott
Promoting Fairness in GNNs: A Characterization of Stability. (1%)Yaning Jia; Chunhui Zhang
2023-09-06
Certifying LLM Safety against Adversarial Prompting. (99%)Aounon Kumar; Chirag Agarwal; Suraj Srinivas; Aaron Jiaxun Li; Soheil Feizi; Himabindu Lakkaraju
SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series. (84%)Chang George Dong; Liangwei Nathan Zheng; Weitong Chen; Wei Emma Zhang; Lin Yue
Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacy. (68%)Zikai Zhang; Rui Hu
J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News. (38%)Tharindu Kumarage; Amrita Bhattacharjee; Djordje Padejski; Kristy Roschke; Dan Gillmor; Scott Ruston; Huan Liu; Joshua Garland
MIRA: Cracking Black-box Watermarking on Deep Neural Networks via Model Inversion-based Removal Attacks. (22%)Yifan Lu; Wenxuan Li; Mi Zhang; Xudong Pan; Min Yang
My Art My Choice: Adversarial Protection Against Unruly AI. (2%)Anthony Rhodes; Ram Bhagat; Umur Aybars Ciftci; Ilke Demir
VeriDIP: Verifying Ownership of Deep Neural Networks through Privacy Leakage Fingerprints. (1%)Aoting Hu; Zhigang Lu; Renjie Xie; Minhui Xue
A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness. (1%)Ze Peng; Lei Qi; Yinghuan Shi; Yang Gao
2023-09-05
The Adversarial Implications of Variable-Time Inference. (99%)Dudi Biton; Aditi Misra; Efrat Levy; Jaidip Kotak; Ron Bitton; Roei Schuster; Nicolas Papernot; Yuval Elovici; Ben Nassi
Adaptive Adversarial Training Does Not Increase Recourse Costs. (92%)Ian Hardy; Jayanth Yetukuri; Yang Liu
Black-Box Attacks against Signed Graph Analysis via Balance Poisoning. (87%)Jialong Zhou; Yuni Lai; Jian Ren; Kai Zhou
RobustEdge: Low Power Adversarial Detection for Cloud-Edge Systems. (83%)Abhishek Moitra; Abhiroop Bhattacharjee; Youngeun Kim; Priyadarshini Panda
Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach. (4%)Vimal K B; Saketh Bachu; Tanmay Garg; Niveditha Lakshmi Narasimhan; Raghavan Konuru; Vineeth N Balasubramanian
Robust Recommender System: A Survey and Future Directions. (2%)Kaike Zhang; Qi Cao; Fei Sun; Yunfan Wu; Shuchang Tao; Huawei Shen; Xueqi Cheng
Dual Adversarial Alignment for Realistic Support-Query Shift Few-shot Learning. (1%)Siyang Jiang; Rui Fang; Hsi-Wen Chen; Wei Ding; Ming-Syan Chen
2023-09-04
Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddings. (99%)AprilPyone MaungMaung; Isao Echizen; Hitoshi Kiya
Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration. (99%)Fengfan Zhou; Hefei Ling; Yuxuan Shi; Jiazhong Chen; Ping Li
Adv3D: Generating 3D Adversarial Examples in Driving Scenarios with NeRF. (99%)Leheng Li; Qing Lian; Ying-Co