paper-with-me

홈 › Papers

Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning

2023-05-18 · Yinglun Xu, Gagandeep Singh

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 unknown algorithms and requires limited attack budgets and computational resources. We leverage a general framework and find conditions to ensure efficient attack under a general assumption of the learning algorithms. We show that our attack is optimal in our framework under the conditions. We experimentally verify that with limited budgets, our attack efficiently leads the learning agent to various target policies under a diverse set of popular DRL environments and state-of-the-art learners.

📄 PDF Abstract BibTeX arXiv:2305.10681

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning

Similar Papers 제목 키워드 기반

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning

2024-02-15 · Yinglun Xu, Rohan Gumaste, Gagandeep Singh

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 oblivio…

Offline RLreinforcement-learningReinforcement Learning

Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments

2021-02-16 · Amin Rakhsha, Xuezhou Zhang, Xiaojin Zhu, Adish Singla

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)

Online Poisoning Attack Against Reinforcement Learning under Black-box Environments

2024-12-01 · Jianhui Li, Bokang Zhang, Junfeng Wu

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 towar…

reinforcement-learningReinforcement Learning

Broadly Applicable Targeted Data Sample Omission Attacks

2021-05-04 · Guy Barash, Eitan Farchi, Sarit Kraus, Onn Shehory

We introduce a novel clean-label targeted poisoning attack on learning mechanisms. While classical poisoning attacks typically corrupt data via addition, modification and omission, our attack focuses on data omission onl…

PAC learning

A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning

2020-11-02 · Chang Xu, Jun Wang, Yuqing Tang, Francisco Guzman 외

As modern neural machine translation (NMT) systems have been widely deployed, their security vulnerabilities require close scrutiny. Most recently, NMT systems have been found vulnerable to targeted attacks which cause t…

Data PoisoningMachine TranslationNMTTranslation