Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning
Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This paper studies transfer-based black-box attacks on DRL: the attacker crafts observation perturbations on a white-box surrogate agent and feeds them to an unknown victim. We for...
Zexin Li, Rui-Li Yao, Yi-Ming Zeng et al.
· 0 citations