A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning

TL;DR

This paper introduces a novel, stealthy backdoor attack on cooperative multi-agent deep reinforcement learning that embeds triggers in a single agent using spatiotemporal patterns, effectively compromising the entire team.

Contribution

It proposes a new backdoor attack method that is more stealthy and practical, attacking only one agent with spatiotemporal triggers and manipulating reward functions.

Findings

Achieves 91.6% attack success rate

Maintains low performance variance (3.7%)

Effective on VDN and QMIX algorithms

Abstract

Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will perform abnormal actions leading to failures or malicious goals. However, existing proposed backdoors suffer from several issues, e.g., fixed visual trigger patterns lack stealthiness, the backdoor is trained or activated by an additional network, or all agents are backdoored. To this end, in this paper, we propose a novel backdoor attack against c-MADRL, which attacks the entire multi-agent team by embedding the backdoor only in a single agent. Firstly, we introduce adversary spatiotemporal behavior patterns as the backdoor trigger rather than manual-injected fixed visual patterns or instant status and control the attack duration. This method can guarantee the stealthiness and practicality of injected backdoors. Secondly, we hack the original reward function of the backdoored agent via reward reverse and unilateral guidance during training to ensure its adverse influence on the entire team. We evaluate our backdoor attacks on two classic c-MADRL algorithms VDN and QMIX, in a popular c-MADRL environment SMAC. The experimental results demonstrate that our backdoor attacks are able to reach a high attack success rate (91.6\%) while maintaining a low clean performance variance rate (3.7\%).