BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

1 code implementation • 7 Oct 2022 • Chen Gong, Zhou Yang, Yunpeng Bai, Junda He, Jieke Shi, Kecen Li, Arunesh Sinha, Bowen Xu, Xinwen Hou, David Lo, Tianhao Wang

Our experiments conducted on four tasks and four offline RL algorithms expose a disquieting fact: none of the existing offline RL algorithms is immune to such a backdoor attack.

Autonomous Driving Backdoor Attack +4