Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems

תקציר מקורי באנגליתarXiv:2602.16543v2 Announce Type: replace Abstract: Safe reinforcement learning (Safe RL) learns robotic controllers that optimize task rewards under safety constraints, yet observation perturbations can induce safety violations. Existing safety-directed attacks often require access to victim networks, gradients, critics, or explicit specifications -- assumptions rarely met once a controller is deployed as a black box. We propose a demonstration-guided observation attack for analyzing unknown Safe RL controllers. The framework recovers a state constraint and a surrogate policy through inverse constrained reinforcement learning, and learns dynamics from demonstration transitions. Their composed gradient generates bounded observation perturbations without victim parameters, gradients, or que