We present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the training data to induce a targeted misclassification of a test-time input. Inspired by the adversarial robustness achieved by $randomized$ $smoothing$, we show how an off-the-shelf diffusion denoising model can sanitize the tampered training data. We extensively test our defense against seven clean-label poisoning attacks in both $\ell_2$ and $\ell_{\infty}$-norms and reduce their attack success to 0-16% with only a negligible drop in the test accuracy. We compare our defense with existing countermeasures against clean-label poisoning, showing that the defense reduces the attack success the most and offers the best model utility. Our results highlight the need for future work on developing stronger clean-label attacks and using our certified yet practical defense as a strong baseline to evaluate these attacks.
Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regressor's prediction may change under a poisoning attack. Our key insight is that certified regression reduces to voting-based certified classification when using median as a model's primary decision function. Coupling our reduction with existing certified classifiers, we propose six new regressors provably-robust to poisoning attacks. To the extent of our knowledge, this is the first work that certifies the robustness of …
Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via modifying, adding, and/or removing some carefully selected training examples, such that the corrupted classifier makes incorrect predictions as the attacker desires. The key idea of state-of-the-art certified defenses against data poisoning attacks and backdoor attacks is to create a majority vote mechanism to predict the label of a testing example. Moreover, each voter is a base classifier trained on a subset of the training dataset. Classical simple learning algorithms such as k nearest neighbors (kN…
Google（谷歌）；Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for AI（博世人工智能中心）
In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models. To do so, we instantiate the denoised smoothing approach of Salman et al. 2020 by combining a pretrained denoising diffusion probabilistic model and a standard high-accuracy classifier. This allows us to certify 71% accuracy on ImageNet under adversarial perturbations constrained to be within an 2-norm of 0.5, an improvement of 14 percentage points over the prior certified SoTA using any approach, or an improvement of …
Shanghai JiaoTong University（上海交通大学）；The Hong Kong Polytechnic University（香港理工大学）
Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to measure. Random selection based defenses can achieve certified robustness by averaging the classifiers' predictions on the sub-datasets sampled from the training set. This paper proposes a framework of random selection based certified defenses against data poisoning attacks. Specifically, we prove that the random selection schemes that satisfy certain conditions…
In a \emph{data poisoning attack}, an attacker modifies, deletes, and/or inserts some training examples to corrupt the learnt machine learning model. \emph{Bootstrap Aggregating (bagging)} is a well-known ensemble learning method, which trains multiple base models on random subsamples of a training dataset using a base learning algorithm and uses majority vote to predict labels of testing examples. We prove the intrinsic certified robustness of bagging against data poisoning attacks. Specifically, we show that bagging with an arbitrary base learning algorithm provably predicts the same label f…
Data poisoning attacks aim at manipulating model behaviors through distorting training data. Previously, an aggregation-based certified defense, Deep Partition Aggregation (DPA), was proposed to mitigate this threat. DPA predicts through an aggregation of base classifiers trained on disjoint subsets of data, thus restricting its sensitivity to dataset distortions. In this work, we propose an improved certified defense against general poisoning attacks, namely Finite Aggregation. In contrast to DPA, which directly splits the training set into disjoint subsets, our method first splits the traini…
Certified Robustness to Data Poisoning in Gradient-Based Training
Department of Computing, Imperial College London, United Kingdom（帝国理工学院伦敦分校计算机系）；Department of Computer Science, ETH Zurich, Switzerland（苏黎世联邦理工学院计算机科学系）；LogicStar.ai, Switzerland（LogicStar.ai公司）；The Alan Turing Institute, United Kingdom（艾伦·图灵研究所）
School of Computing and Information Systems（计算与信息系统学院）；University of Melbourne（墨尔本大学）；Department of Computer Science（计算机科学系）；Amherst College（阿默斯特学院）
The right to erasure requires removal of a user's information from data held by organizations, with rigorous interpretations extending to downstream products such as learned models. Retraining from scratch with the particular user's data omitted fully removes its influence on the resulting model, but comes with a high computational cost. Machine "unlearning" mitigates the cost incurred by full retraining: instead, models are updated incrementally, possibly only requiring retraining when approximation errors accumulate. Rapid progress has been made towards privacy guarantees on the indistinguis…
LASIGE（LASIGE实验室）；Faculdade de Ciências da Universidade Lisboa（里斯本大学理学院）
Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with the initial training data. In order to defend DNNs against such adversarial attacks, this work proposes a novel method that combines the defensive distillation mechanism with a denoising autoencoder (DAE). This technique tries to lower the sensitivity of the distilled model to poison attacks by spotting and reconstructing poisonous adversarial inputs in the training data. We add…
Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-尚佩恩分校）；IBM Research（IBM研究院）；UC Berkeley（加州大学伯克利分校）；Amazon Web Services（亚马逊云服务）；Stanford University（斯坦福大学）
Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the learned model. While recent work has proposed a number of attacks and defenses, little is understood about the worst-case loss of a defense in the face of a determined attacker. We address this by constructing approximate upper bounds on the loss across a broad family of attacks, for defenders that first perform outlier removal followed by empirical risk minimization. Our approximation relies on two assumptions: (1) …
Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph learning tasks. However, recent studies show that GNNs are vulnerable to both test-time evasion and training-time poisoning attacks that perturb the graph structure. While existing attack methods have shown promising attack performance, we would like to design an attack framework to further enhance the performance. In particular, our attack framework is inspired by certified robustness, which was originally used by defenders to defend against adversarial attacks. We are the first, from the attacker perspectiv…
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for AI（博世人工智能中心）
Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized smoothing over arbitrary functions, and we leverage this novel characterization to propose a new strategy for building classifiers that are pointwise-certifiably robust to general data poisoning attacks. As a specific instantiation, we utilize our framework to build linear classifiers that are robust to a strong variant of label flipping, where each test exam…
Data poisoning considers an adversary that distorts the training set of machine learning algorithms for malicious purposes. In this work, we bring to light one conjecture regarding the fundamentals of data poisoning, which we call the Lethal Dose Conjecture. The conjecture states: If $n$ clean training samples are needed for accurate predictions, then in a size-$N$ training set, only $Θ(N/n)$ poisoned samples can be tolerated while ensuring accuracy. Theoretically, we verify this conjecture in multiple cases. We also offer a more general perspective of this conjecture through distribution disc…
CPR: Causal Physiological Representation Learning for Robust ECG Analysis under Distribution Shifts
Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China（创新工程学院，澳门科技大学，澳门，中国）；Shenzhen University of Advanced Technology, Shenzhen, China（深圳先进技术大学，深圳，中国）
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Max Planck Institute for Software Systems (MPI-SWS)（马克斯·普朗克软件系统研究所（MPI-SWS））
In reward-poisoning attacks against reinforcement learning (RL), an attacker can perturb the environment reward $r_t$ into $r_t+δ_t$ at each step, with the goal of forcing the RL agent to learn a nefarious policy. We categorize such attacks by the infinity-norm constraint on $δ_t$: We provide a lower threshold below which reward-poisoning attack is infeasible and RL is certified to be safe; we provide a corresponding upper threshold above which the attack is feasible. Feasible attacks can be further categorized as non-adaptive where $δ_t$ depends only on $(s_t,a_t, s_{t+1})$, or adaptive where…
Arizona State University（亚利桑那州立大学）；NVIDIA（英伟达）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；Caltech（加州理工学院）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；UC Berkeley（加州大学伯克利分校）
Diffusion models have been recently employed to improve certified robustness through the process of denoising. However, the theoretical understanding of why diffusion models are able to improve the certified robustness is still lacking, preventing from further improvement. In this study, we close this gap by analyzing the fundamental properties of diffusion models and establishing the conditions under which they can enhance certified robustness. This deeper understanding allows us to propose a new method DensePure, designed to improve the certified robustness of a pretrained model (i.e. classi…
Carnegie Mellon University（卡内基梅隆大学）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Purdue University（普渡大学）
Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the results of a learning system. In this work, we show how to achieve strong robustness guarantees in the face of such attacks across multiple axes. We provide robustly-reliable predictions, in which the predicted label is guaranteed to be correct so long as the adversary has not exceeded a given corruption budget, even in the presence of instance targeted attacks,…
Federated Learning (FL) is a distributed learning paradigm that enables different parties to train a model together for high quality and strong privacy protection. In this scenario, individual participants may get compromised and perform backdoor attacks by poisoning the data (or gradients). Existing work on robust aggregation and certified FL robustness does not study how hardening benign clients can affect the global model (and the malicious clients). In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting. Moreo…
ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification
National Engineering Research Center for Big Data Technology and System（国家大数据技术与系统工程研究中心）；Hubei Engineering Research Center on Big Data Security（湖北省大数据安全工程研究中心）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）；Services Computing Technology and System Lab（服务计算技术与系统实验室）；Cluster and Grid Computing Lab（集群与网格计算实验室）；Hubei Key Laboratory of Distributed System Security（湖北省分布式系统安全重点实验室）；School of Cyber Science and Engineering, Huazhong University of Science and Technology（华中科技大学网络空间科学与工程学院）
