Resilient Learning-Based Control for Synchronization of Passive Multi-Agent Systems under Attack

TL;DR

This paper develops a resilient, distributed control framework for multi-agent systems that ensures synchronization under communication constraints and Byzantine attacks by integrating event-triggered control, attack detection, and learning-based mitigation strategies.

Contribution

It introduces a novel learning-based control method combined with decentralized attack detection to maintain synchronization despite Byzantine adversaries in passive multi-agent systems.

Findings

Guarantees synchronization with reduced communication load.

Effectively detects and identifies Byzantine neighbors.

Mitigates attack effects using learning-based control strategies.

Abstract

In this paper, we show synchronization for a group of output passive agents that communicate with each other according to an underlying communication graph to achieve a common goal. We propose a distributed event-triggered control framework that will guarantee synchronization and considerably decrease the required communication load on the band-limited network. We define a general Byzantine attack on the event-triggered multi-agent network system and characterize its negative effects on synchronization. The Byzantine agents are capable of intelligently falsifying their data and manipulating the underlying communication graph by altering their respective control feedback weights. We introduce a decentralized detection framework and analyze its steady-state and transient performances. We propose a way of identifying individual Byzantine neighbors and a learning-based method of estimating the attack parameters. Lastly, we propose learning-based control approaches to mitigate the negative effects of the adversarial attack.