Hybrid-driven-based H∞ filter design for neural networks subject to deception attacks

This paper investigates the problem of H-infinity filter design for neural networks with hybrid triggered scheme and deception attacks. In order to make full use of the limited network resources, a hybrid triggered scheme is introduced, in which the switching between the time triggered scheme and the event triggered scheme obeys Bernoulli distribution. By considering the effect of hybrid triggered scheme and deception attacks, a mathematical model of H-infinity filtering error system is constructed. The sufficient conditions that can ensure the stability of filtering error system are given by using Lyapunov stability theory and linear matrix inequality (LMI) techniques. Moreover, the explicit expressions are provided for the designed filter parameters that is in terms of LMIs. Finally, a numerical example is employed to illustrate the design method. (C) 2017 Elsevier Inc. All rights reserved.