Backdoor Attacks On Multiagent Collaborative Systems

Abstract

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can arbitrarily modify the victim's observations, which may not be practical. One work proposes to let one adversary agent use its actions to affect its opponent in two-agent competitive games, so that the opponent quickly fails after observing certain trigger actions. However, in multiagent collaborative systems, agents may not always be able to observe others. When and how much the adversary agent can affect others are uncertain, and we want the adversary agent to trigger others for as few times as possible. To solve this problem, we first design a novel training framework to produce auxiliary rewards that measure the extent to which the other agents'observations being affected. Then we use the auxiliary rewards to train a trigger policy which enables the a

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2022backdoor

Related papers

• A Spatiotemporal Stealthy Backdoor Attack Against Cooperative Multi-agent Deep Reinforcement Learning (2024)0.00
• Constrained Black-box Attacks Against Cooperative Multi-agent Reinforcement Learning (2025)0.00
• Policycleanse: Backdoor Detection And Mitigation In Reinforcement Learning (2022)0.00
• Recover Triggered States: Protect Model Against Backdoor Attack In Reinforcement Learning (2023)0.00
• Adversarial Inception Backdoor Attacks Against Reinforcement Learning (2024)0.00
• Provable Defense Against Backdoor Policies In Reinforcement Learning (2022)2.26
• Cooperative Backdoor Attack In Decentralized Reinforcement Learning With Theoretical Guarantee (2024)0.00
• SUB-PLAY: Adversarial Policies Against Partially Observed Multi-agent Reinforcement Learning Systems (2024)0.00