Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning

ArXi:2602.05089v3 Announce Type: replace-cross Simulated environments are a key piece in the success of Reinforcement Learning (RL), allowing practitioners and researchers to train decision making agents without running expensive experiments on real hardware. Simulators remain a security blind spot, however, enabling adversarial developers to alter the dynamics of their released simulators for malicious purposes. Therefore, in this work we highlight a novel threat, nstrating how simulator dynamics can be exploited to stealthily implant action-level backdoors into RL agents.