Universal Trojan Signatures in Reinforcement Learning
Manoj Acharya ⋅ Weichao Zhou ⋅ Anirban Roy ⋅ Xiao Lin ⋅ Wenchao Li ⋅ Susmit Jha
2023 Poster
in
Workshop: Backdoors in Deep Learning: The Good, the Bad, and the Ugly
in
Workshop: Backdoors in Deep Learning: The Good, the Bad, and the Ugly
Abstract
We present a novel approach for characterizing Trojaned reinforcement learning (RL) agents. By monitoring for discrepancies in how an agent's policy evaluates state observations for choosing an action, we can reliably detect whether the policy is Trojaned. Experiments on the IARPA RL challenge benchmarks show that our approach can effectively detect Trojaned models even in transfer settings with novel RL environments and modified architectures.
Chat is not available.
Successful Page Load