Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
We study the problem of universal black-boxed reward poisoning attacks against general offline reinforcement learning with deep neural networks. We consider a black-box threat model where the attacker is entirely oblivious to the learning algorithm, and its budget is limited by constraining the amount of corruption at each data point and the total perturbation. We require the attack to be universally efficient against any efficient algorithms that might be used by the agent. We propose an attack strategy called the `policy contrast attack.' The idea is to find low- and high-performing policies covered by the dataset and make them appear to be high- and low-performing to the agent, respectively. To the best of our knowledge, we propose the first universal black-box reward poisoning attack in the general offline RL setting. We provide theoretical insights on the attack design and empirically show that our attack is efficient against current state-of-the-art offline RL algorithms in different learning datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Offline RLreinforcement-learningReinforcement LearningSimilar Papers 제목 키워드 기반
Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
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…
reinforcement-learningReinforcement Learning (RL)Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning
We propose the first black-box targeted attack against online deep reinforcement learning through reward poisoning during training time. Our attack is applicable to general environments with unknown dynamics learned by u…
Deep Reinforcement Learningreinforcement-learningSleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial att…
Backdoor Attackreinforcement-learningReinforcement LearningReinforcement Learning (RL)Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning
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 ad…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning
Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become a core technology for tasks such as question-answering (QA) and content generation. RAG poisoning is an attack method to indu…
Reinforcement Learning