BehaviorGuard detects backdoor behaviors in DRL policies via behavioral drift in action distributions and suppresses suspicious actions at runtime, claimed as the first online defense for both single- and multi-agent settings.
A temporal-pattern backdoor attack to deep reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning
BehaviorGuard detects backdoor behaviors in DRL policies via behavioral drift in action distributions and suppresses suspicious actions at runtime, claimed as the first online defense for both single- and multi-agent settings.