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 unknown to the adversary a priori. That is, our attack makes minimum assumptions on the prior knowledge of the adversary: it has no initial knowledge of the environment or the learner, and neither does it observe the learner's internal mechanism except for its performed actions. We design a novel black-box attack, U2, that can provably achieve a near-matching performance to the state-of-the-art white-box attack, demonstrating the feasibility of reward poisoning even in the most challenging black-box setting.
@article{arxiv.2102.08492,
title = {Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments},
author = {Amin Rakhsha and Xuezhou Zhang and Xiaojin Zhu and Adish Singla},
journal= {arXiv preprint arXiv:2102.08492},
year = {2021}
}