Cyber-Attack Detection in Discrete Nonlinear Multi-Agent Systems Using Neural Networks

TL;DR

This paper introduces a neural network-based distributed detection method for cyber-attacks in discrete nonlinear multi-agent systems, ensuring stability and attack detectability through Lyapunov-based analysis.

Contribution

It presents a novel residual-based detection system using neural network observers tailored for nonlinear multi-agent systems with proven stability and attack detection capabilities.

Findings

Effective detection of false data injection attacks demonstrated in simulations

Proven stability and boundedness of the detection residuals

Enhanced security in multi-agent communication channels

Abstract

This paper proposes a distributed cyber-attack detection method in communication channels for a class of discrete, nonlinear, heterogeneous, multi-agent systems that are controlled by our proposed formation-based controller. A residual-based detection system, exploiting a neural network (NN)-based observer, is developed to detect false data injection attacks on agents communication channels. A Lyapunov function is used to derive the NN weights tuning law and the attack detectability threshold. The uniform ultimate boundedness (UUB) of the detector residual and formation error is proven based on the Lyapunov stability theory. The proposed methods attack detectability properties are analyzed, and simulation results demonstrate the proposed detection methodologys performance.