AI RESEARCH
Plan2Cleanse: Test-Time Backdoor Defense via Monte-Carlo Planning in Deep Reinforcement Learning
arXiv CS.LG
•
ArXi:2605.09638v1 Announce Type: new Ensuring the security of reinforcement learning (RL) models is critical, particularly when they are trained by third parties and deployed in real-world systems. Attackers can implant backdoors into these models, causing them to behave normally under typical conditions, but execute malicious behaviors when specific triggers are activated. In this work, we propose Plan2Cleanse, a test-time detection and mitigation framework that adapts Monte Carlo Tree Search to efficiently identify and neutralize RL backdoor attacks without requiring model re.