arXiv Machine Learning July 7, 2026 By Jose Efraim Aguilar Escamilla, Haoyang Hong, Jiawei Li, Haoyu Zhao, Xuezhou Zhang, Sanghyun Hong, Huazheng Wang

When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs

Read the original on arXiv Machine Learning →

arXiv:2604. 10062v3 Announce Type: replace Abstract: 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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 9

Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks

arXiv:2506. 06891v3 Announce Type: replace Abstract: We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al.

By Paulius Sasnauskas, Yi\u{g}it Yal{\i}n, Goran Radanovi\'c

llms reinforcement-learning safety

arXiv Machine Learning

Jul 24

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.

By Chenlong Yin, Runpeng Geng, Yanting Wang, Jinyuan Jia

llms agents reinforcement-learning efficiency benchmarks safety

arXiv AI

Jun 4

A Systematic Investigation of RL-Jailbreaking in LLMs

arXiv:2605. 07032v2 Announce Type: replace-cross Abstract: The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening.

By Montaser Mohammedalamen, Kevin Roice, Reginald McLean, Alyssa Lefaivre \v{S}kopac

llms agents reinforcement-learning robotics safety

arXiv AI

Jun 9

Safe-RULE: Safe Reinforcement UnLEarning

arXiv:2606. 09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such as robotics systems.

By Shixiong Jiang, Taozheng Zhu, Fanxin Kong

reinforcement-learning robotics benchmarks safety

arXiv AI

Jun 6

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

arXiv:2503. 01734v3 Announce Type: replace-cross Abstract: Attacks on machine learning models have been extensively studied through stateless optimization.

By Kyle Domico, Jean-Charles Noirot Ferrand, Ryan Sheatsley, Eric Pauley, Josiah Hanna, Patrick McDaniel

agents computer-vision reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 25

Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning

arXiv:2505. 19532v2 Announce Type: replace Abstract: The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or rewards.

By Shijie Liu, Andrew C. Cullen, Paul Montague, Sarah Erfani, Benjamin I. P. Rubinstein

agents reinforcement-learning benchmarks

Related stories

Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

A Systematic Investigation of RL-Jailbreaking in LLMs

Safe-RULE: Safe Reinforcement UnLEarning

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning