Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee

Understand

The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents.

• The paper investigates a cooperative backdoor attack in a decentralized reinforcement learning scenario.
• Differing from the existing methods that hide a whole backdoor attack behind their shared policies, our method decomposes the backdoor behavior into multiple components according to the state space of RL.
• Each malicious agent hides one component in its policy and shares its policy with the benign agents.