We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes average reward in undiscounted infinite-horizon problem settings. The attacker can manipulate the rewards or the transition dynamics in the learning environment at training-time and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an \emph{optimal stealthy attack} for different measures of attack cost. We provide sufficient technical conditions under which the attack is feasible and provide lower/upper bounds on the attack cost. We instantiate our attacks in two settings: (i) an \emph{offline} setting where the agent is doing planning in the poisoned environment, and (ii) an \emph{online} setting where the agent is learning a policy using a regret-minimization framework with poisoned feedback. Our results show that the attacker can easily succeed in teaching any target policy to the victim under mild conditions and highlight a significant security threat to reinforcement learning agents in practice.
Max Planck Institute for Software Systems (MPI-SWS)（马克斯·普朗克软件系统研究所）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes reward in infinite-horizon problem settings. The attacker can manipulate the rewards and the transition dynamics in the learning environment at training-time, and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an optimal stealthy attack for different measures of attack cost. We provide…
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…
Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
We study reward design strategies for incentivizing a reinforcement learning agent to adopt a policy from a set of admissible policies. The goal of the reward designer is to modify the underlying reward function cost-efficiently while ensuring that any approximately optimal deterministic policy under the new reward function is admissible and performs well under the original reward function. This problem can be viewed as a dual to the problem of optimal reward poisoning attacks: instead of forcing an agent to adopt a specific policy, the reward designer incentivizes an agent to avoid taking act…
Due to the broad range of applications of reinforcement learning (RL), understanding the effects of adversarial attacks against RL model is essential for the safe applications of this model. Prior theoretical works on adversarial attacks against RL mainly focus on either observation poisoning attacks or environment poisoning attacks. In this paper, we introduce a new class of attacks named action poisoning attacks, where an adversary can change the action signal selected by the agent. Compared with existing attack models, the attacker's ability in the proposed action poisoning attack model is …
University of Maryland, College Park（马里兰大学帕克分校）；Shanghai Jiao Tong University（上海交通大学）
Poisoning attacks on Reinforcement Learning (RL) systems could take advantage of RL algorithm's vulnerabilities and cause failure of the learning. However, prior works on poisoning RL usually either unrealistically assume the attacker knows the underlying Markov Decision Process (MDP), or directly apply the poisoning methods in supervised learning to RL. In this work, we build a generic poisoning framework for online RL via a comprehensive investigation of heterogeneous poisoning models in RL. Without any prior knowledge of the MDP, we propose a strategic poisoning algorithm called Vulnerabili…
Contextual bandit algorithms have many applicants in a variety of scenarios. In order to develop trustworthy contextual bandit systems, understanding the impacts of various adversarial attacks on contextual bandit algorithms is essential. In this paper, we propose a new class of attacks: action poisoning attacks, where an adversary can change the action signal selected by the agent. We design action poisoning attack schemes against linear contextual bandit algorithms in both white-box and black-box settings. We further analyze the cost of the proposed attack strategies for a very popular and w…
Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks
Department of Computing Science, University of Alberta, Edmonton, Canada.（阿尔伯塔大学计算机科学系，加拿大埃德蒙顿）；Alberta Machine Intelligence Institute (Amii), Edmonton, Canada.（阿尔伯塔机器智能研究所（Amii），加拿大埃德蒙顿）
I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, including test-item attacks, training-data poisoning, and adversarial reward shaping. The view encourages adversarial machine learning researcher to utilize advances in control theory and reinforcement learning.
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…
Federated learning, as a distributed learning that conducts the training on the local devices without accessing to the training data, is vulnerable to Byzatine poisoning adversarial attacks. We argue that the federated learning model has to avoid those kind of adversarial attacks through filtering out the adversarial clients by means of the federated aggregation operator. We propose a dynamic federated aggregation operator that dynamically discards those adversarial clients and allows to prevent the corruption of the global learning model. We assess it as a defense against adversarial attacks …
Imperial College London（帝国理工学院）；Hasso Plattner Institut, University of Potsdam（波茨坦大学哈索·普拉特纳研究所）；Princeton University（普林斯顿大学）
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-level optimization problem. Solving these problems is computationally demanding and has limited applicability for some models such as deep networks. In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers genera…
University of South Florida（南佛罗里达大学）；Fordham University（福特汉姆大学）
Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning attacks really questions the robustness of ML models. For instance, Engstrom et al. demonstrated that state-of-the-art image classifiers could be easily fooled by a small rotation on an arbitrary image. As ML systems are being increasingly integrated into safety and security-sensitive applications, adversarial attacks and data poisoning attacks pose a considera…
Northeastern University（东北大学）；University of Cagliari（卡利亚里大学）；Pluribus One
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transferability has been shown in previous work, but the underlying reasons why an attack transfers or not are not yet well understood. In this paper, we present a comprehensive analysis aimed to investigate the transferability of both test-time evasion and training-time poisoning attacks. We provide a unifying optimization framework for evasion and poisoning attacks, and a formal definition of transferability of such attacks…
Indraprastha Institute of Information Technology Delhi（德里英德拉普拉斯塔信息技术学院）
Learning low-level node embeddings using techniques from network representation learning is useful for solving downstream tasks such as node classification and link prediction. An important consideration in such applications is the robustness of the embedding algorithms against adversarial attacks, which can be examined by performing perturbation on the original network. An efficient perturbation technique can degrade the performance of network embeddings on downstream tasks. In this paper, we study network embedding algorithms from an adversarial point of view and observe the effect of poison…
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms to extract valuable information from data and produce accurate predictions, it has been shown that these algorithms are vulnerable to attacks. Data poisoning is one of the most relevant security threats against machine learning systems, where attackers can subvert the learning process by injecting malicious samples in the training data. Recent work in adversa…
Graph convolutional neural networks, which learn aggregations over neighbor nodes, have achieved great performance in node classification tasks. However, recent studies reported that such graph convolutional node classifier can be deceived by adversarial perturbations on graphs. Abusing graph convolutions, a node's classification result can be influenced by poisoning its neighbors. Given an attributed graph and a node classifier, how can we evaluate robustness against such indirect adversarial attacks? Can we generate strong adversarial perturbations which are effective on not only one-hop nei…
The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks. However, despite the proliferation of such methods, there is currently no study of their robustness to adversarial attacks. We provide the first adversarial vulnerability analysis on the widely used family of methods based on random walks. We derive efficient adversarial perturbations that poison the network structure and have a negative effect on both the quality of the embeddings and the downstream tasks. We further show that ou…
University of Maryland（马里兰大学）；University of Siegen（锡根大学）
The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained models, are even more effective for data poisoning than recent methods designed specifically for poisoning. Our findings indicate that adversarial examples, when assigned the original label of their natural base image, cannot be used to train a classifier for natural images. Furthermore, when adversarial examples are assigned their adversarial class label, th…
In recent years, a variety of effective neural network-based methods for anomaly and cyber attack detection in industrial control systems (ICSs) have been demonstrated in the literature. Given their successful implementation and widespread use, there is a need to study adversarial attacks on such detection methods to better protect the systems that depend upon them. The extensive research performed on adversarial attacks on image and malware classification has little relevance to the physical system state prediction domain, which most of the ICS attack detection systems belong to. Moreover, su…
University of Siegen（锡根大学）；University of Maryland（马里兰大学）
Data poisoning is a threat model in which a malicious actor tampers with training data to manipulate outcomes at inference time. A variety of defenses against this threat model have been proposed, but each suffers from at least one of the following flaws: they are easily overcome by adaptive attacks, they severely reduce testing performance, or they cannot generalize to diverse data poisoning threat models. Adversarial training, and its variants, are currently considered the only empirically strong defense against (inference-time) adversarial attacks. In this work, we extend the adversarial tr…
University of Arkansas at Fayetteville（阿肯色大学费耶特维尔分校）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
Both fair machine learning and adversarial learning have been extensively studied. However, attacking fair machine learning models has received less attention. In this paper, we present a framework that seeks to effectively generate poisoning samples to attack both model accuracy and algorithmic fairness. Our attacking framework can target fair machine learning models trained with a variety of group based fairness notions such as demographic parity and equalized odds. We develop three online attacks, adversarial sampling , adversarial labeling, and adversarial feature modification. All three a…
Continuous learning from streaming data is among the most challenging topics in the contemporary machine learning. In this domain, learning algorithms must not only be able to handle massive volumes of rapidly arriving data, but also adapt themselves to potential emerging changes. The phenomenon of the evolving nature of data streams is known as concept drift. While there is a plethora of methods designed for detecting its occurrence, all of them assume that the drift is connected with underlying changes in the source of data. However, one must consider the possibility of a malicious injection…
Adversarial Machine Learning has emerged as a substantial subfield of Computer Science due to a lack of robustness in the models we train along with crowdsourcing practices that enable attackers to tamper with data. In the last two years, interest has surged in adversarial attacks on graphs yet the Graph Classification setting remains nearly untouched. Since a Graph Classification dataset consists of discrete graphs with class labels, related work has forgone direct gradient optimization in favor of an indirect Reinforcement Learning approach. We will study the novel problem of Data Poisoning …
This paper examines the robustness of deployed few-shot meta-learning systems when they are fed an imperceptibly perturbed few-shot dataset. We attack amortized meta-learners, which allows us to craft colluding sets of inputs that are tailored to fool the system's learning algorithm when used as training data. Jointly crafted adversarial inputs might be expected to synergistically manipulate a classifier, allowing for very strong data-poisoning attacks that would be hard to detect. We show that in a white box setting, these attacks are very successful and can cause the target model's predictio…
University of South Florida（南佛罗里达大学）；U.S. Air Force Research Laboratory（美国空军研究实验室）
Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language processing. Although a lot of data is created each day by active Internet users, most of these data are unlabeled and are vulnerable to data poisoning attacks. In this paper, we develop an efficient active learning method that requires fewer labeled instances and incorporates the technique of adversarial retraining in which additional labeled artificial data are generated without increasing the budget of the labeling. …
Pennsylvania State University（宾夕法尼亚州立大学）；University of Central Florida（中佛罗里达大学）
Graph neural networks (GNNs) are widely used in many applications. However, their robustness against adversarial attacks is criticized. Prior studies show that using unnoticeable modifications on graph topology or nodal features can significantly reduce the performances of GNNs. It is very challenging to design robust graph neural networks against poisoning attack and several efforts have been taken. Existing work aims at reducing the negative impact from adversarial edges only with the poisoned graph, which is sub-optimal since they fail to discriminate adversarial edges from normal ones. On …
University of California Merced（加州大学默塞德分校）；Tagliatela College of Engineering（塔利亚泰拉工程学院）；University of New Haven（纽黑文大学）
State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques that are only applicable to specific machine learning models. Additionally, the existing data poisoning attacks in the literature are limited to either binary classifiers or to gradient-based algorithms. To address these limitations, this paper first proposes a novel model-free label-flipping attack based on the multi-modality of the data, in which the adversar…
Making learners robust to adversarial perturbation at test time (i.e., evasion attacks) or training time (i.e., poisoning attacks) has emerged as a challenging task. It is known that for some natural settings, sublinear perturbations in the training phase or the testing phase can drastically decrease the quality of the predictions. These negative results, however, are information theoretic and only prove the existence of such successful adversarial perturbations. A natural question for these settings is whether or not we can make classifiers computationally robust to polynomial-time attacks. I…
Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e., lowering the overall model accuracy) or integrity attacks (i.e., enabling specific instance-based backdoor). In this paper, we advance the adversarial objectives of the availability attacks to a per-class basis, which we refer to as class-oriented poisoning attacks. We demonstrate that the proposed attack is capable of forcing the corrupted model to predict in…
Universitat Pomepu Fabra（庞培法布拉大学）；Università degli Studi di Cagliari（卡利亚里大学）
Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model accuracy of such poisoning attacks have been widely studied, their potential effects on other model performance metrics remain to be evaluated. In this work, we introduce an optimization framework for poisoning attacks against algorithmic fairness, and develop a gradient-based poisoning attack aimed at introducing classification disparities among different groups i…
Bharati Vidyapeeth’s College of Engineering（巴拉蒂维迪佩斯工程学院）；IIT Delhi（印度理工学院德里分校）
Traditional adversarial attacks rely upon the perturbations generated by gradients from the network which are generally safeguarded by gradient guided search to provide an adversarial counterpart to the network. In this paper, we propose a novel mechanism of generating adversarial examples where the actual image is not corrupted rather its latent space representation is utilized to tamper with the inherent structure of the image while maintaining the perceptual quality intact and to act as legitimate data samples. As opposed to gradient-based attacks, the latent space poisoning exploits the in…
College of Computer National University of Defense Technology（国防科技大学计算机学院）
In big data era, machine learning is one of fundamental techniques in intrusion detection systems (IDSs). However, practical IDSs generally update their decision module by feeding new data then retraining learning models in a periodical way. Hence, some attacks that comprise the data for training or testing classifiers significantly challenge the detecting capability of machine learning-based IDSs. Poisoning attack, which is one of the most recognized security threats towards machine learning-based IDSs, injects some adversarial samples into the training phase, inducing data drifting of traini…
Clustering algorithms play a fundamental role as tools in decision-making and sensible automation processes. Due to the widespread use of these applications, a robustness analysis of this family of algorithms against adversarial noise has become imperative. To the best of our knowledge, however, only a few works have currently addressed this problem. In an attempt to fill this gap, in this work, we propose a black-box adversarial attack for crafting adversarial samples to test the robustness of clustering algorithms. We formulate the problem as a constrained minimization program, general in it…
Toyota Technological Institute Chicago（芝加哥丰田技术研究所）
A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical data; however, the model reliably errs on watermarked examples. To gain a better foundational understanding of backdoor data poisoning attacks, we present a formal theoretical framework within which one can discuss backdoor data poisoning attacks for classification problems. We then use this to analyze important statistical and computational issues surrounding…
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…
Many modern machine learning classifiers are shown to be vulnerable to adversarial perturbations of the instances. Despite a massive amount of work focusing on making classifiers robust, the task seems quite challenging. In this work, through a theoretical study, we investigate the adversarial risk and robustness of classifiers and draw a connection to the well-known phenomenon of concentration of measure in metric measure spaces. We show that if the metric probability space of the test instance is concentrated, any classifier with some initial constant error is inherently vulnerable to advers…
Imperial College London（帝国理工学院）；DIEE, University of Cagliari（卡利亚里大学电气与电子工程系）；Pluribus One
A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction of the training data is controlled by the attacker and manipulated to subvert the learning process. To date, these attacks have been devised only against a limited class of binary learning algorithms, due to the inherent complexity of the gradient-based procedure used to optimize the poisoning points (a.k.a. adversarial training examples). In this work, we …
