USENIX Security, 2021.
Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training, while requiring 100x less labeled data.
We study a new class of vulnerabilities: poisoning attacks that modify the unlabeled dataset. In order to be useful, unlabeled datasets are given strictly less review than labeled datasets, and adversaries can therefore poison them easily. By inserting maliciously-crafted unlabeled examples totaling just 0.1% of the dataset size, we can manipulate a model trained on this poisoned dataset to misclassify arbitrary examples at test time (as any desired label). Our attacks are highly effective across datasets and semi-supervised learning methods.
We find that more accurate methods (thus more likely to be used) are significantly more vulnerable to poisoning attacks, and as such better training methods are unlikely to prevent this attack. To counter this we explore the space of defenses, and propose two methods that mitigate our attack.
USENIX Security, 2021.
Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, Alina Oprea, Colin Raffel
It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary can perform a training data extraction attack to recover individual training examples by querying the language model.
We demonstrate our attack on GPT-2, a language model trained on scrapes of the public Internet, and are able to extract hundreds of verbatim text sequences from the model's training data. These extracted examples include (public) personally identifiable information (names, phone numbers, and email addresses), IRC conversations, code, and 128-bit UUIDs. Our attack is possible even though each of the above sequences are included in just one document in the training data.
We comprehensively evaluate our extraction attack to understand the factors that contribute to its success. For example, we find that larger models are more vulnerable than smaller models. We conclude by drawing lessons and discussing possible safeguards for training large language models.
IEEE S&P, 2021.
Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, Florian Tramer
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy. In this work, we study whether a non-private learning algorithm can be made private by relying on an instance-encoding mechanism that modifies the training inputs before feeding them to a normal learner. We formalize both the notion of instance encoding and its privacy by providing two attack models. We first prove impossibility results for achieving a (stronger) model. Next, we demonstrate practical attacks in the second (weaker) attack model on InstaHide, a recent proposal by Huang, Song, Li and Arora [ICML'20] that aims to use instance encoding for privacy.
IEEE S&P, 2021.
Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini
Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a dataset D, or a dataset D' that differs in just one example.
If observing the training algorithm does not meaningfully increase the adversary's odds of successfully guessing which dataset the model was trained on, then the algorithm is said to be differentially private. Hence, the purpose of privacy analysis is to upper bound the probability that any adversary could successfully guess which dataset the model was trained this http URL our paper, we instantiate this hypothetical adversary in order to establish lower bounds on the probability that this distinguishing game can be won. We use this adversary to evaluate the importance of the adversary capabilities allowed in the privacy analysis of DP training algorithms.
For DP-SGD, the most common method for training neural networks with differential privacy, our lower bounds are tight and match the theoretical upper bound. This implies that in order to prove better upper bounds, it will be necessary to make use of additional assumptions. Fortunately, we find that our attacks are significantly weaker when additional (realistic)restrictions are put in place on the adversary's capabilities.Thus, in the practical setting common to many real-world deployments, there is a gap between our lower bounds and the upper bounds provided by the analysis: differential privacy is conservative and adversaries may not be able to leak as much information as suggested by the theoretical bound.
Florian Tramer, Nicholas Carlini, Wieland Brendel, Aleksander Madry
Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at ICLR, ICML and NeurIPS---and chosen for illustrative and pedagogical purposes---can be circumvented despite attempting to perform evaluations using adaptive attacks. While prior evaluation papers focused mainly on the end result---showing that a defense was ineffective---this paper focuses on laying out the methodology and the approach necessary to perform an adaptive attack. We hope that these analyses will serve as guidance on how to properly perform adaptive attacks against defenses to adversarial examples, and thus will allow the community to make further progress in building more robust models.
Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang, Colin Raffel
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model’s performance. This domain has seen fast progress recently, at the cost of requiring more complex methods. In this paper we propose FixMatch, an algorithm that is a significant simplification of existing SSL methods. FixMatch first generates pseudo-labels using the model’s predictions on weaklyaugmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image. Despite its simplicity, we show that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks, including 94.93% accuracy on CIFAR-10 with 250 labels and 88.61% accuracy with 40 – just 4 labels per class. We carry out an extensive ablation study to tease apart the experimental factors that are most important to FixMatch’s success. The code is available at https://github.com/google-research/fixmatch.
Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Benjamin Recht, Ludwig Schmidt
We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets. Most research on robustness focuses on synthetic image perturbations (noise, simulated weather artifacts, adversarial examples, etc.), which leaves open how robustness on synthetic distribution shift relates to distribution shift arising in real data. Informed by an evaluation of 204 ImageNet models in 213 different test conditions, we find that there is often little to no transfer of robustness from current synthetic to natural distribution shift. Moreover, most current techniques provide no robustness to the natural distribution shifts in our testbed. The main exception is training on larger and more diverse datasets, which in multiple cases increases robustness, but is still far from closing the performance gaps. Our results indicate that distribution shifts arising in real data are currently an open research problem.
Nicholas Carlini, Matthew Jagielski, Ilya Mironov
We argue that the machine learning problem of model extraction is actually a cryptanalytic problem in disguise, and should be studied as such. Given oracle access to a neural network, we introduce a differential attack that can efficiently steal the parameters of the remote model up to floating point precision. Our attack relies on the fact that ReLU neural networks are piecewise linear functions, and thus queries at the critical points reveal information about the model parameters.
We evaluate our attack on multiple neural network models and extract models that are 2^20 times more precise and require 100x fewer queries than prior work. For example, we extract a 100,000 parameter neural network trained on the MNIST digit recognition task with 2^21.5 queries in under an hour, such that the extracted model agrees with the oracle on all inputs up to a worst-case error of 2^-25, or a model with 4,000 parameters in 2^18.5 queries with worst-case error of 2^-40.4.
USENIX Security, 2020.
Matthew Jagielski, Nicholas Carlini, David Berthelot, Alex Kurakin, and Nicolas Papernot
In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: accuracy, i.e., performing well on the underlying learning task, and fidelity, i.e., matching the predictions of the remote victim classifier on any input.
To extract a high-accuracy model, we develop a learning-based attack exploiting the victim to supervise the training of an extracted model. Through analytical and empirical arguments, we then explain the inherent limitations that prevent any learning-based strategy from extracting a truly high-fidelity model—i.e., extracting a functionally-equivalent model whose predictions are identical to those of the victim model on all possible inputs. Addressing these limitations, we expand on prior work to develop the first practical functionally-equivalent extraction attack for direct extraction (i.e., without training) of a model’s weights.
We perform experiments both on academic datasets and a state-of-the-art image classifier trained with 1 billion proprietary images. In addition to broadening the scope of model extraction research, our work demonstrates the practicality of model extraction attacks against production-grade systems.
Florian Tramèr, Jens Behrmann, Nicholas Carlini, Nicolas Papernot, Jörn-Henrik Jacobsen
Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied sensitivity-based adversarial examples introduce semantically-small changes to an input that result in a different model prediction. This paper studies a complementary failure mode, invariance-based adversarial examples, that introduce minimal semantic changes that modify an input's true label yet preserve the model's prediction. We demonstrate fundamental tradeoffs between these two types of adversarial examples.
We show that defenses against sensitivity-based attacks actively harm a model's accuracy on invariance-based attacks, and that new approaches are needed to resist both attack types. In particular, we break state-of-the-art adversarially-trained and certifiably-robust models by generating small perturbations that the models are (provably) robust to, yet that change an input's class according to human labelers. Finally, we formally show that the existence of excessively invariant classifiers arises from the presence of overly-robust predictive features in standard datasets.
CVPR Workshop on Media Forensics, 2020.
Nicholas Carlini, Hany Farid
It is now possible to synthesize highly realistic images of people who do not exist. Such content has, for example, been implicated in the creation of fraudulent social-media profiles responsible for dis-information campaigns. Significant efforts are, therefore, being deployed to detect synthetically-generated content. One popular forensic approach trains a neural network to distinguish real from synthetic content.
We show that such forensic classifiers are vulnerable to a range of attacks that reduce the classifier to near-0% accuracy. We develop five attack case studies on a state-of-the-art classifier that achieves an area under the ROC curve (AUC) of 0.95 on almost all existing image generators, when only trained on one generator. With full access to the classifier, we can flip the lowest bit of each pixel in an image to reduce the classifier's AUC to 0.0005; perturb 1% of the image area to reduce the classifier's AUC to 0.08; or add a single noise pattern in the synthesizer's latent space to reduce the classifier's AUC to 0.17. We also develop a black-box attack that, with no access to the target classifier, reduces the AUC to 0.22. These attacks reveal significant vulnerabilities of certain image-forensic classifiers.
David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel
We improve the recently-proposed “MixMatch” semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels. Augmentation anchoring feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input. To produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained. Our new algorithm, dubbed ReMixMatch, is significantly more data-efficient than prior work, requiring between 5x and 16x less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach 93.73% accuracy (compared to MixMatch's accuracy of 93.58% with 4,000 examples) and a median accuracy of 84.92% with just four labels per class. We make our code and data open-source at https://github.com/google-research/remixmatch
David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, Colin Raffel
Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that works by guessing low-entropy labels for data-augmented unlabeled examples and mixing labeled and unlabeled data using MixUp. We show that MixMatch obtains state-of-the-art results by a large margin across many datasets and labeled data amounts. For example, on CIFAR-10 with 250 labels, we reduce error rate by a factor of 4 (from 38% to 11%) and by a factor of 2 on STL-10. We also demonstrate how MixMatch can help achieve a dramatically better accuracy-privacy trade-off for differential privacy. Finally, we perform an ablation study to tease apart which components of MixMatch are most important for its success.
USENIX Security, 2019.
Nicholas Carlini, Chang Liu, Ulfar Erlingsson, Jernej Kos, Dawn Song
This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence models—a common type of machine-learning model. Because such models are sometimes trained on sensitive data (e.g., the text of users' private messages), this methodology can benefit privacy by allowing deep-learning practitioners to select means of training that minimize such memorization.
In experiments, we show that unintended memorization is a persistent, hard-to-avoid issue that can have serious consequences. Specifically, for models trained without consideration of memorization, we describe new, efficient procedures that can extract unique, secret sequences, such as credit card numbers. We show that our testing strategy is a practical and easy-to-use first line of defense, e.g., by describing its application to quantitatively limit data exposure in Google's Smart Compose, a commercial text-completion neural network trained on millions of users' email messages.
Nic Ford, Justin Gilmer, Nicholas Carlini, Dogus Cubuk
Over the last few years, the phenomenon of adversarial examples --- maliciously constructed inputs that fool trained machine learning models --- has captured the attention of the research community, especially when the adversary is restricted to small modifications of a correctly handled input. Less surprisingly, image classifiers also lack human-level performance on randomly corrupted images, such as images with additive Gaussian noise. In this paper we provide both empirical and theoretical evidence that these are two manifestations of the same underlying phenomenon, establishing close connections between the adversarial robustness and corruption robustness research programs. This suggests that improving adversarial robustness should go hand in hand with improving performance in the presence of more general and realistic image corruptions. Based on our results we recommend that future adversarial defenses consider evaluating the robustness of their methods to distributional shift with benchmarks such as Imagenet-C.
Yao Qin, Nicholas Carlini, Ian Goodfellow, Garrison Cottrell, Colin Raffel
Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can be constructed by imperceptibly modifying images to cause misclassification, and are practical in the physical world. In contrast, current targeted adversarial examples applied to speech recognition systems have neither of these properties: humans can easily identify the adversarial perturbations, and they are not effective when played over-the-air. This paper makes advances on both of these fronts. First, we develop effectively imperceptible audio adversarial examples (verified through a human study) by leveraging the psychoacoustic principle of auditory masking, while retaining 100% targeted success rate on arbitrary full-sentence targets. Next, we make progress towards physical-world over-the-air audio adversarial examples by constructing perturbations which remain effective even after applying realistic simulated environmental distortions.
SafeML ICLR Workshop, 2019.
Jörn-Henrik Jacobsen, Jens Behrmannn, Nicholas Carlini, Florian Tramèr, Nicolas Papernot
Adversarial examples are malicious inputs crafted to cause a model to misclassify them. Their most common instantiation, "perturbation-based" adversarial examples introduce changes to the input that leave its true label unchanged, yet result in a different model prediction. Conversely, "invariance-based" adversarial examples insert changes to the input that leave the model's prediction unaffected despite the underlying input's label having changed.
In this paper, we demonstrate that robustness to perturbation-based adversarial examples is not only insufficient for general robustness, but worse, it can also increase vulnerability of the model to invariance-based adversarial examples. In addition to analytical constructions, we empirically study vision classifiers with state-of-the-art robustness to perturbation-based adversaries constrained by an lp norm. We mount attacks that exploit excessive model invariance in directions relevant to the task, which are able to find adversarial examples within the lp ball. In fact, we find that classifiers trained to be lp-norm robust are more vulnerable to invariance-based adversarial examples than their undefended counterparts.
Excessive invariance is not limited to models trained to be robust to perturbation-based lp-norm adversaries. In fact, we argue that the term adversarial example is used to capture a series of model limitations, some of which may not have been discovered yet. Accordingly, we call for a set of precise definitions that taxonomize and address each of these shortcomings in learning.
arXiv (unpublished), 2019.
Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian Goodfellow, Aleksander Madry
Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers that propose defenses are quickly shown to be incorrect.
We believe a large contributing factor is the difficulty of performing security evaluations. In this paper, we discuss the methodological foundations, review commonly accepted best practices, and suggest new methods for evaluating defenses to adversarial examples. We hope that both researchers developing defenses as well as readers and reviewers who wish to understand the completeness of an evaluation consider our advice in order to avoid common pitfalls.
arXiv (unpublished), 2018.
Tom B. Brown, Nicholas Carlini, Chiyuan Zhang, Catherine Olsson, Paul Christiano, Ian Goodfellow
We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to unconstrained adversaries. Defenders submit machine learning models, and try to achieve high accuracy and coverage on non-adversarial data while making no confident mistakes on adversarial inputs. Attackers try to subvert defenses by finding arbitrary unambiguous inputs where the model assigns an incorrect label with high confidence. We propose a simple unambiguous dataset ("bird-or-bicycle") to use as part of this contest. We hope this contest will help to more comprehensively evaluate the worst-case adversarial risk of machine learning models.
International Conference on Machine Learning, 2018. Best Paper.
Anish Athalye*, Nicholas Carlini*, and David Wagner
We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative optimization-based attacks, we find defenses relying on this effect can be circumvented. We describe characteristic behaviors of defenses exhibiting the effect, and for each of the three types of obfuscated gradients we discover, we develop attack techniques to overcome it. In a case study, examining non-certified white-box-secure defenses at ICLR 2018, we find obfuscated gradients are a common occurrence, with 7 of 9 defenses relying on obfuscated gradients. Our new attacks successfully circumvent 6 completely, and 1 partially, in the original threat model each paper considers.* Equal Contribution
Deep Learning and Security Workshop, 2018. Best Paper.
Nicholas Carlini and David Wagner
ACM Workshop on Artificial Intelligence and Security, 2017. Finalist, Best Paper.
Nicholas Carlini and David Wagner
USENIX Workshop on Offensive Technologies, 2017.
Warren He, James Wei, Xinyun Chen, Nicholas Carlini, Dawn Song
IEEE Symposium on Security and Privacy, 2017. Best Student Paper.
Nicholas Carlini and David Wagner
Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x' that is similar to x but classified as t. This makes it difficult to apply neural networks in security-critical areas. Defensive distillation is a recently proposed approach that can take an arbitrary neural network, and increase its robustness, reducing the success rate of current attacks’ ability to find adversarial examples from 95% to 0.5%.
In this paper, we demonstrate that defensive distillation does not significantly increase the robustness of neural networks by introducing three new attack algorithms that are successful on both distilled and undistilled neural networks with 100% probability. Our attacks are tailored to three distance metrics used previously in the literature, and when compared to previous adversarial example generation algorithms, our attacks are often much more effective (and never worse). Furthermore, we propose using high-confidence adversarial examples in a simple transferability test we show can also be used to break defensive distillation. We hope our attacks will be used as a benchmark in future defense attempts to create neural networks that resist adversarial examples.
USENIX Security, 2016. CSAW Best Applied Research Paper.
Nicholas Carlini*, Pratyush Mishra*, Tavish Vaidya*, Yuankai Zhang*, Micah Sherr, Clay Shields, David Wagner, and Wenchao Zhou
Voice interfaces are becoming more ubiquitous and are now the primary input method for many devices. We explore in this paper how they can be attacked with hidden voice commands that are unintelligible to human listeners but which are interpreted as commands by devices.
We evaluate these attacks under two different threat models. In the black-box model, an attacker uses the speech recognition system as an opaque oracle. We show that the adversary can produce difficult to understand commands that are effective against existing systems in the black-box model. Under the white-box model, the attacker has full knowledge of the internals of the speech recognition system and uses it to create attack commands that we demonstrate through user testing are not understandable by humans.
We then evaluate several defenses, including notifying the user when a voice command is accepted; a verbal challenge-response protocol; and a machine learning approach that can detect our attacks with 99.8% accuracy.
USENIX Security, 2015.
Nicholas Carlini, Antonio Barresi, Mathias Payer, Thomas R. Gross and David Wagner
Control-Flow Integrity (CFI) is a defense which prevents control-flow hijacking attacks. While recent research has shown that coarse-grained CFI does not stop attacks, fine-grained CFI is believed to be secure.
We argue that assessing the effectiveness of practical CFI implementations is non-trivial and that common evaluation metrics fail to do so. We then evaluate fully-precise static CFI -- the most restrictive CFI policy that does not break functionality -- and reveal limitations in its security. Using a generalization of non-control-data attacks which we call Control-Flow Bending (CFB), we show how an attacker can leverage a memory corruption vulnerability to achieve Turing-complete computation on memory using just calls to the standard library. We use this attack technique to evaluate fully-precise static CFI on six real binaries and show that in five out of six cases, powerful attacks are still possible. Our results suggest that CFI may not be a reliable defense against memory corruption vulnerabilities.
We further evaluate shadow stacks in combination with CFI and find that their presence for security is necessary: deploying shadow stacks removes arbitrary code execution capabilities of attackers in three of six cases.
USENIX Security, 2014.
Nicholas Carlini and David Wagner
USENIX Journal of Election Technology and Systems (JETS), Volume 1 Issue 1. Presented at EVT/WOTE 2013.
Eric Kim, Nicholas Carlini, Andrew Chang, George Yiu, Kai Wang, and David Wagner
Kai Wang, Eric Kim, Nicholas Carlini, Ivan Motyashov, Daniel Nguyen, and David Wagner
USENIX Security, 2012.
Nicholas Carlini, Adrienne Porter Felt, and David Wagner
arXiv short paper, 2019.
arXiv short paper, 2019.
Computer Vision: Challenges and Opportunities for Privacy and Security, 2018.
Anish Athalye and Nicholas Carlini
arXiv short paper, 2017.
Nicholas Carlini and David Wagner
arXiv short paper, 2016.
Nicholas Carlini and David Wagner