Resilient and privacy-preserving consensus for multi-agent systems

Abstract

Privacy concerns and cyber-attacks are two typical threats in networked multi-agent systems (MASs), while little research has properly addressed both. To fill this gap, we investigate a privacy-preserving consensus strategy against cyber-attacks for MASs. First, a novel network eavesdropper model and a cyber-attack model that is more strategic than existing literature are proposed. Then, a homomorphic encryption-based mean subsequence reduced (HE-MSR) consensus algorithm equipped with a privacy protection strategy is designed for each normal agent. The results reveal that the privacy of states of all normal agents and the accurate consensus are guaranteed under mild network topology conditions. Furthermore, these results are extended to the case of a time-varying MAS network environment. Finally, numerical simulations and hardware experiments on Raspberry Pi are conducted to verify the theoretical results.