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

Jinliang Liu, Jilei Xia, Engang Tian and Shumin Fei

Applied Mathematics and Computation, 2018, vol. 320, issue C, 158-174

Abstract: This paper investigates the problem of H∞ 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∞ 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.

Keywords: Neural networks; Hybrid triggered scheme; H∞ filter design; Deception attacks (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (12)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0096300317306276
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:apmaco:v:320:y:2018:i:c:p:158-174

DOI: 10.1016/j.amc.2017.09.007

Access Statistics for this article

Applied Mathematics and Computation is currently edited by Theodore Simos

More articles in Applied Mathematics and Computation from Elsevier
Bibliographic data for series maintained by Catherine Liu ().