Data poisoning for reinforcement learning has historically focused on general performance degradation, and targeted attacks have been successful via perturbations that involve control of the victim's policy and rewards. We introduce an insidious poisoning attack for reinforcement learning which causes agent misbehavior only at specific target states - all while minimally modifying a small fraction of training observations without assuming any control over policy or reward. We accomplish this by adapting a recent technique, gradient alignment, to reinforcement learning. We test our method and demonstrate success in two Atari games of varying difficulty.
University of California San Diego（加州大学圣地亚哥分校）；University of Virginia（弗吉尼亚大学）；University of Warwick（华威大学）
To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential damage of two natural types of poisoning attacks, i.e., the manipulation of \emph{reward} and \emph{action}. We discover that the effect of attacks crucially depend on whether the rewards are bounded or unbounded. In bounded reward settings, we show that only reward manipulation or only action manipulation cannot guarantee a successful attack. However, by c…
In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP primitives, such as rewards or transitions. In this paper, we study targeted poisoning attacks in a two-agent setting where an attacker implicitly poisons the effective environment of one of the agents by modifying the policy of its peer. We develop an optimization framework for designing optimal attacks, where the cost of the attack measures how much the solution…
BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning
University of Chinese Academy of Sciences（中国科学院大学）；INRIA（法国国家信息与自动化研究所）；Microsoft Azure AI（微软Azure人工智能）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Online Poisoning Attack Against Reinforcement Learning under Black-box Environments
College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；School of Science and Engineering, Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）
University of Virginia（弗吉尼亚大学）；Princeton University（普林斯顿大学）
In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider poisoning attacks against convex machine learning models and propose an efficient poisoning attack designed to induce a specified model. Unlike previous model-targeted poisoning attacks, our attack comes with provable convergence to {\it any} attainable target classifier. The distance from the induced classifier to the target classifier is inversely proportional to the square root …
Efficient Preference Poisoning Attack on Offline RLHF
Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA（加州大学戴维斯分校电气与计算机工程系）；Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA, USA（爱荷华大学电气与计算机工程系）
When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USA（电子工程与计算机科学学院，俄勒冈州立大学，俄勒冈州科瓦利斯）；Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, Illinois, USA（电气与计算机工程系，伊利诺伊大学厄巴纳-香槟分校，伊利诺伊州厄巴纳）；Princeton University, Princeton, New Jersey, USA（普林斯顿大学，新泽西州普林斯顿）；Faculty of Computing and Data Sciences, Boston University, Boston, Massachusetts, USA（计算与数据科学学院，波士顿大学，马萨诸塞州波士顿）
In this paper, we study PAC learnability and certification of predictions under instance-targeted poisoning attacks, where the adversary who knows the test instance may change a fraction of the training set with the goal of fooling the learner at the test instance. Our first contribution is to formalize the problem in various settings and to explicitly model subtle aspects such as the proper or improper nature of the learning, learner's randomness, and whether (or not) adversary's attack can depend on it. Our main result shows that when the budget of the adversary scales sublinearly with the s…
This chapter studies emerging cyber-attacks on reinforcement learning (RL) and introduces a quantitative approach to analyze the vulnerabilities of RL. Focusing on adversarial manipulation on the cost signals, we analyze the performance degradation of TD($λ$) and $Q$-learning algorithms under the manipulation. For TD($λ$), the approximation learned from the manipulated costs has an approximation error bound proportional to the magnitude of the attack. The effect of the adversarial attacks on the bound does not depend on the choice of $λ$. In $Q$-learning, we show that $Q$-learning algorithms c…
Boston University（波士顿大学）；SRI International（斯坦福国际研究院）
Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep reinforcement learning (DRL) agents and can be exploited by an adversary with access to the training process. In particular, we focus on Trojan attacks that augment the function of reinforcement learning policies with hidden behaviors. We demonstrate that such attacks can be implemented through minuscule data poisoning (as little as 0.025% of the training data) and…
Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many security-sensitive applications like payment apps. Such usages of deep learning systems provide the adversaries with sufficient incentives to perform attacks against these systems for their adversarial purposes. In this work, we consider a new type of attacks, called backdoor attacks, where the attacker's goal is to create a backdoor into a learning-based a…
The University of Tokyo（东京大学）；RIKEN AIP（理化学研究所先进智能项目中心）；University of Tsukuba（筑波大学）
Model poisoning attacks on federated learning (FL) intrude in the entire system via compromising an edge model, resulting in malfunctioning of machine learning models. Such compromised models are tampered with to perform adversary-desired behaviors. In particular, we considered a semi-targeted situation where the source class is predetermined however the target class is not. The goal is to cause the global classifier to misclassify data of the source class. Though approaches such as label flipping have been adopted to inject poisoned parameters into FL, it has been shown that their performance…
Princeton University（普林斯顿大学）；University of Chicago（芝加哥大学）；IBM
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on targeted sub-tasks (e.g. classifying planes as birds) by uploading "poisoned" updates. In this report we introduce \algoname{}, a novel defense that uses global top-k update sparsification and device-level gradient clipping to mitigate model poisoning attacks. We propose a theoretical framework for analyzing the robustness of defenses against poisoning attacks…
University of Maryland, College Park（马里兰大学帕克分校）；United States Naval Academy（美国海军学院）；Cornell University（康奈尔大学）
Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks that succeed without access to the victim network's outputs, architecture, or (in some cases) training data. To achieve this, we propose a new "polytope attack" in which poison images are designed to surround the targeted image in feature space. We also demonstrate that using Dropout during poison creation helps to enhance transferability of this attack. We …
University of Maryland（马里兰大学）；Cornell University（康奈尔大学）
Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks use "clean-labels"; they don't require the attacker to have any control over the labeling of training data. They are also targeted; they control the behavior of the classifier on a $\textit{specific}$ test instance without degrading overall classifier performance. For example, an attacker could add a seemingly innocuous image (that is properly labeled) to a t…
Tel Aviv University（特拉维夫大学）；Cornell Tech（康奈尔理工学院）；Cornell University（康奈尔大学）；Columbia University（哥伦比亚大学）
Code autocompletion is an integral feature of modern code editors and IDEs. The latest generation of autocompleters uses neural language models, trained on public open-source code repositories, to suggest likely (not just statically feasible) completions given the current context. We demonstrate that neural code autocompleters are vulnerable to poisoning attacks. By adding a few specially-crafted files to the autocompleter's training corpus (data poisoning), or else by directly fine-tuning the autocompleter on these files (model poisoning), the attacker can influence its suggestions for attack…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data. Existing defenses are often effective only against a specific type of targeted attack, significantly degrade the generalization performance, or are prohibitive for standard deep learning pipelines. In this work, we propose an efficient defense mechanism that significantly reduces the success rate of various data poisoning attacks, and provides theoretical guarantees for the performance of the model. Targeted attacks work by adding bounded perturbations to a random…
School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）
News Recommendation System(NRS) has become a fundamental technology to many online news services. Meanwhile, several studies show that recommendation systems(RS) are vulnerable to data poisoning attacks, and the attackers have the ability to mislead the system to perform as their desires. A widely studied attack approach, injecting fake users, can be applied on the NRS when the NRS is treated the same as the other systems whose items are fixed. However, in the NRS, as each item (i.e. news) is more informative, we propose a novel approach to poison the NRS, which is to perturb contents of some …
Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the distributed nature of FL gives rise to new threats caused by potentially malicious participants. In this paper, we study targeted data poisoning attacks against FL systems in which a malicious subset of the participants aim to poison the global model by sending model updates derived from mislabeled data. We first demonstrate that such data poisoning attacks c…
Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
Department of Mathematics, Technion（技术学院数学系）；Departments of Mathematics, Computer Science, and Data and Decision Sciences, Technion and Google Research（技术学院数学系、计算机科学系和数据与决策科学系，以及谷歌研究）
Recent results suggest that attacks against supervised machine learning systems are quite effective, while defenses are easily bypassed by new attacks. However, the specifications for machine learning systems currently lack precise adversary definitions, and the existing attacks make diverse, potentially unrealistic assumptions about the strength of the adversary who launches them. We propose the FAIL attacker model, which describes the adversary's knowledge and control along four dimensions. Our model allows us to consider a wide range of weaker adversaries who have limited control and incomp…
Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
Department of Electronics Engineering, Tsinghua University, Beijing, China（清华大学电子工程系）；College of AI, Tsinghua University, Beijing, China（清华大学人工智能学院）；Beijing National Research Center for Information Science and Technology, Beijing, China（北京信息科学国家研究中心）
Poisoning Attacks on Federated Learning for Autonomous Driving
Umeå University（于默奥大学）；AI Sweden（瑞典人工智能研究院）；Royal Institute of Technology（皇家理工学院）；Chalmers University of Technology（查尔姆斯理工大学）；Dakota State University（达科他州立大学）；Scaleout Systems（Scaleout系统公司）
University of Maryland, College Park（马里兰大学帕克分校）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Machine learning algorithms are vulnerable to data poisoning attacks. Prior taxonomies that focus on specific scenarios, e.g., indiscriminate or targeted, have enabled defenses for the corresponding subset of known attacks. Yet, this introduces an inevitable arms race between adversaries and defenders. In this work, we study the feasibility of an attack-agnostic defense relying on artifacts that are common to all poisoning attacks. Specifically, we focus on a common element between all attacks: they modify gradients computed to train the model. We identify two main artifacts of gradients compu…
In this work, we present a data poisoning attack that confounds machine learning models without any manipulation of the image or label. This is achieved by simply leveraging the most confounding natural samples found within the training data itself, in a new form of a targeted attack coined "Mole Recruitment." We define moles as the training samples of a class that appear most similar to samples of another class, and show that simply restructuring training batches with an optimal number of moles can lead to significant degradation in the performance of the targeted class. We show the efficacy …
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an indiscriminate way. Label flipping attacks are a special case of data poisoning, where the attacker can control the labels assigned to a fraction of the training points. Even if the capabilities of the attacker are constrained, these attacks have been shown to be effective to signif…
VenoMave: Targeted Poisoning Against Speech Recognition
University of California, Santa Barbara（加州大学圣巴巴拉分校）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Ruhr University Bochum（波鸿鲁尔大学）；Technische Universität Berlin（柏林工业大学）
Purdue University（普渡大学）；Yale University（耶鲁大学）；Google Research（谷歌研究院）；University of Virginia（弗吉尼亚大学）；Technion（以色列理工学院）
Consider the task of learning a hypothesis class $\mathcal{H}$ in the presence of an adversary that can replace up to an $η$ fraction of the examples in the training set with arbitrary adversarial examples. The adversary aims to fail the learner on a particular target test point $x$ which is known to the adversary but not to the learner. In this work we aim to characterize the smallest achievable error $ε=ε(η)$ by the learner in the presence of such an adversary in both realizable and agnostic settings. We fully achieve this in the realizable setting, proving that $ε=Θ(\mathtt{VC}(\mathcal{H})…
University of Siegen（锡根大学）；University of Maryland（马里兰大学）；US Naval Academy（美国海军学院）
Data Poisoning attacks modify training data to maliciously control a model trained on such data. In this work, we focus on targeted poisoning attacks which cause a reclassification of an unmodified test image and as such breach model integrity. We consider a particularly malicious poisoning attack that is both "from scratch" and "clean label", meaning we analyze an attack that successfully works against new, randomly initialized models, and is nearly imperceptible to humans, all while perturbing only a small fraction of the training data. Previous poisoning attacks against deep neural networks…
SUNY at Buffalo（纽约州立大学布法罗分校）；Alibaba Group（阿里巴巴集团）；Zhejiang University（浙江大学）
Knowledge graph embedding (KGE) is a technique for learning continuous embeddings for entities and relations in the knowledge graph.Due to its benefit to a variety of downstream tasks such as knowledge graph completion, question answering and recommendation, KGE has gained significant attention recently. Despite its effectiveness in a benign environment, KGE' robustness to adversarial attacks is not well-studied. Existing attack methods on graph data cannot be directly applied to attack the embeddings of knowledge graph due to its heterogeneity. To fill this gap, we propose a collection of dat…
Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor and poisoning attacks a significant threat. By poisoning just 0.01% of a dataset (e.g., just 300 images of the 3 million-example Conceptual Captions dataset), we can cause the model to misclassify test images by overlaying a small patch. Targeted poisoning attacks, whereby the model misclassifies a particular test input with an adversarially-desired label, ar…
Duke University（杜克大学）；University of Science and Technology of China（中国科学技术大学）
Federated learning is vulnerable to poisoning attacks in which malicious clients poison the global model via sending malicious model updates to the server. Existing defenses focus on preventing a small number of malicious clients from poisoning the global model via robust federated learning methods and detecting malicious clients when there are a large number of them. However, it is still an open challenge how to recover the global model from poisoning attacks after the malicious clients are detected. A naive solution is to remove the detected malicious clients and train a new global model fro…
