Backdoor Detection in Reinforcement Learning Agents for Electric Vehicle Charging Control

As electric vehicles become central to modern transportation, power grids increasingly rely on automated reinforcement learning controllers. This study investigates whether backdoored RL agents controlling simulated EV charging systems can be detected using lightweight statistical anomaly detectors and compact neural models. We evaluate detection methods operating solely on state-action trajectories without access to model internals. Across multiple random seeds and held-out evaluation runs, neural classifiers achieved near-perfect separation between clean and compromised agents, while statistical methods exhibited high recall but elevated false alarm rates.