Litcius/Paper detail

Quasisynchronization of Reaction–Diffusion Neural Networks Under Deception Attacks

Ruimei Zhang, Hongxia Wang, Ju H. Park, Hak‐Keung Lam, Peisong He

2022IEEE Transactions on Systems Man and Cybernetics Systems44 citationsDOIOpen Access PDF

Abstract

This study focuses on the quasisynchronization problem for reaction–diffusion neural networks (RDNNs) in the presence of deception attacks. Under deception attacks, a time–space sampled-data (TSSD) control mechanism is proposed for RDNNs. Compared with traditional control strategies, the proposed control mechanism can not only save network bandwidth but also improve the cybersecurity of communications. Inspired by Halanay’s inequality, a new inequality is proposed, which can be effectively applied to the quasisynchronization problem for dynamical systems. Then, by using this inequality and the Lyapunov functional approach, quasisynchronization criteria are set for RDNNs. The desired control gain is gained from solving a group of linear matrix inequalities. Moreover, in the absence of deception attacks, the exponential synchronization problem is studied for RDNNs. In the end, simulation results are given to demonstrate the usefulness of the theoretical analysis.

Topics & Concepts

DeceptionSynchronization (alternating current)Artificial neural networkComputer scienceReaction–diffusion systemSet (abstract data type)Control (management)Control theory (sociology)MathematicsArtificial intelligenceLawTelecommunicationsProgramming languagePolitical scienceChannel (broadcasting)Mathematical analysisNeural Networks Stability and SynchronizationAdvanced Memory and Neural ComputingNonlinear Dynamics and Pattern Formation