AINeutralarXiv – CS AI · 6h ago7/10
🧠
BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning
Researchers propose BehaviorGuard, an online defense framework against backdoor attacks in deep reinforcement learning that detects malicious behavior by analyzing action distribution shifts rather than relying on reward anomalies or model fine-tuning. The approach works in both single and multi-agent DRL environments and demonstrates superior efficacy and efficiency compared to existing defense methods.