Litcius/Paper detail

Complex Dynamic Networks for Multiple Attacks: A Jump-Like Event-Triggered Controller Based on Neural Network Model

Jianan Zhang, Yuechao Ma

2024IEEE Transactions on Network Science and Engineering11 citationsDOI

Abstract

This article designs a jump-like event-triggered control based on the neural network model for complex dynamic networks (CDNs) under multiple attacks. First, the multiple cyberattack model is constructed by considering the aperiodic denial of service (DoS) attacks and deception attacks. In this regard, DoS attacks that limit the frequency and duration of different nodes and deception attacks that eliminate strict assumptions are studied. Second, a novel jump-like event-triggered controller based on neural network is proposed. It can not only adaptively jump between different threshold parameters based on whether DoS attacks occur, but also use weighted neural network to approximate and reduce the adverse influence from deception attacks. Next, by establishing the Lyapunov function and utilizing the integral inequality method, the sufficient conditions for ensuring the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${H_\infty }$</tex-math></inline-formula> exponential synchronization of the system are obtained. Ultimately, the effectiveness of the proposed results are demonstrated through the Chua's circuit.

Topics & Concepts

Computer scienceJumpArtificial neural networkControl theory (sociology)Controller (irrigation)Artificial intelligenceControl (management)PhysicsBiologyAgronomyQuantum mechanicsNetwork Security and Intrusion DetectionNeural Networks Stability and Synchronizationstochastic dynamics and bifurcation