Intrusion detection techniques based on improved intuitionistic fuzzy neural networks. (2017)

• Record Type: Journal Article
• Authors: Lei, Yang; Kong, Weiwei; Ma, Jing
• Is Part Of: International journal of innovative computing and applications. Volume 8:Number 1(2017)
• Page Start: 41
• Page End: 49
• Publication Date: 2017
• Subjects: intrusion detection -- intuitionistic fuzzy neural networks -- non-subsampled shearlet transform -- NSST -- computer security -- intuitionistic fuzzy sets -- IFSs -- artificial neural networks -- ANNs -- multi-scale geometry analysis -- MGA -- attacks; Evolutionary computation -- Periodicals; Neural networks (Computer science) -- Periodicals; Genetic programming (Computer science) -- Periodicals; Biologically-inspired computing -- Periodicals; Swarm intelligence -- Periodicals; Quantum computers -- Periodicals; 006.3
• Languages: English
• ISSNs: 1751-648X

Abstract

At present, the issue of intrusion detection has been a hot point in the computer security area. In this paper, three novel intrusion detection schemes have been proposed. First, unlike the current existent detection methods, this paper combines the theories of both intuitionistic fuzzy sets (IFSs) and artificial neural networks (ANNs) together, which lead to much fewer iteration numbers, higher detection rates and sufficient stability. Then, we address anther novel scheme based on non-subsampled shearlet transform (NSST) domain ANNs to solve those problems, including employing multi-scale geometry analysis (MGA) of NSST and the train characteristics of ANN together. Lastly, an efficient anomaly analysis proves to be more efficient and less complex than the existing techniques. The approach relies on monitoring the security state by using a set of accurate metrics. NSST is used to decompose these metrics. Attacks are viewed as singularities that arise in some specific points of time.