English
Related papers

Related papers: Defense Against Reward Poisoning Attacks in Reinfo…

200 papers

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…

Machine Learning · Computer Science 2020-11-24 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

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…

Machine Learning · Computer Science 2020-08-20 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

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…

Machine Learning · Computer Science 2022-08-30 Anshuka Rangi , Haifeng Xu , Long Tran-Thanh , Massimo Franceschetti

We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives. Prior works on…

Machine Learning · Computer Science 2026-04-16 Jose Efraim Aguilar Escamilla , Haoyang Hong , Jiawei Li , Haoyu Zhao , Xuezhou Zhang , Sanghyun Hong , Huazheng Wang

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…

Machine Learning · Computer Science 2022-01-07 Kiarash Banihashem , Adish Singla , Jiarui Gan , Goran Radanovic

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…

Machine Learning · Computer Science 2023-02-28 Mohammad Mohammadi , Jonathan Nöther , Debmalya Mandal , Adish Singla , Goran Radanovic

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed…

Machine Learning · Computer Science 2019-08-02 Alessio Russo , Alexandre Proutiere

We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch…

Machine Learning · Computer Science 2019-11-01 Yuzhe Ma , Xuezhou Zhang , Wen Sun , Xiaojin Zhu

As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of…

Cryptography and Security · Computer Science 2021-09-29 Matthew Jagielski , Alina Oprea , Battista Biggio , Chang Liu , Cristina Nita-Rotaru , Bo Li

In reward-poisoning attacks against reinforcement learning (RL), an attacker can perturb the environment reward $r_t$ into $r_t+\delta_t$ at each step, with the goal of forcing the RL agent to learn a nefarious policy. We categorize such…

Machine Learning · Computer Science 2020-06-24 Xuezhou Zhang , Yuzhe Ma , Adish Singla , Xiaojin Zhu

In offline multi-agent reinforcement learning (MARL), agents estimate policies from a given dataset. We study reward-poisoning attacks in this setting where an exogenous attacker modifies the rewards in the dataset before the agents see the…

Machine Learning · Computer Science 2023-03-09 Young Wu , Jeremy McMahan , Xiaojin Zhu , Qiaomin Xie

Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study…

Machine Learning · Computer Science 2022-05-17 Chao Wang

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Theoretical Economics · Economics 2020-03-24 Arthur Charpentier , Romuald Elie , Carl Remlinger

Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions…

Machine Learning · Computer Science 2024-10-10 Junlin Wu , Jiongxiao Wang , Chaowei Xiao , Chenguang Wang , Ning Zhang , Yevgeniy Vorobeychik

We study automated intrusion prevention using reinforcement learning. In a novel approach, we formulate the problem of intrusion prevention as an optimal stopping problem. This formulation allows us insight into the structure of the optimal…

Artificial Intelligence · Computer Science 2024-04-23 Kim Hammar , Rolf Stadler

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of…

Machine Learning · Computer Science 2020-02-21 Yizhen Wang , Somesh Jha , Kamalika Chaudhuri

Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically trained in cyber gym environments using dense, highly…

Machine Learning · Computer Science 2026-02-13 Elizabeth Bates , Chris Hicks , Vasilios Mavroudis

To ensure the usefulness of Reinforcement Learning (RL) in real systems, it is crucial to ensure they are robust to noise and adversarial attacks. In adversarial RL, an external attacker has the power to manipulate the victim agent's…

Machine Learning · Computer Science 2024-06-18 Jeremy McMahan , Young Wu , Xiaojin Zhu , Qiaomin Xie

This paper proposes an online environment poisoning algorithm tailored for reinforcement learning agents operating in a black-box setting, where an adversary deliberately manipulates training data to lead the agent toward a mischievous…

Machine Learning · Computer Science 2024-12-03 Jianhui Li , Bokang Zhang , Junfeng Wu

We study black-box reward poisoning attacks against reinforcement learning (RL), in which an adversary aims to manipulate the rewards to mislead a sequence of RL agents with unknown algorithms to learn a nefarious policy in an environment…

Machine Learning · Computer Science 2021-02-18 Amin Rakhsha , Xuezhou Zhang , Xiaojin Zhu , Adish Singla
‹ Prev 1 2 3 10 Next ›