A Hypergraph and Arithmetic Residue-based Probabilistic Neural Network for classification in Intrusion Detection Systems. (August 2017)

• Record Type: Journal Article
• Authors: Raman, M.R. Gauthama; Somu, Nivethitha; Kirthivasan, Kannan; Sriram, V.S. Shankar
• Is Part Of: Neural networks. Volume 92(2017)
• Page Start: 89
• Page End: 97
• Publication Date: 2017-08
• Subjects: Intrusion Detection Systems (IDSs) -- Artificial Neural Network (ANN) -- Feature selection and classification -- Probabilistic Neural Network (PNN) -- Arithmetic Residue (AR) -- Hypergraph (HG); Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2017.01.012
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Over the past few decades, the design of an intelligent Intrusion Detection System (IDS) remains an open challenge to the research community. Continuous efforts by the researchers have resulted in the development of several learning models based on Artificial Neural Network (ANN) to improve the performance of the IDSs. However, there exists a tradeoff with respect to the stability of ANN architecture and the detection rate for less frequent attacks. This paper presents a novel approach based on Helly property of Hypergraph and Arithmetic Residue-based Probabilistic Neural Network (HG AR-PNN) to address the classification problem in IDS. The Helly property of Hypergraph was exploited for the identification of the optimal feature subset and the arithmetic residue of the optimal feature subset was used to train the PNN. The performance of HG AR-PNN was evaluated using KDD CUP 1999 intrusion dataset. Experimental results prove the dominance of HG AR-PNN classifier over the existing classifiers with respect to the stability and improved detection rate for less frequent attacks. Highlights: A Hypergraph and Arithmetic Residue based PNN (HG AR-PNN) is proposed for IDS. HG AR-PNN uses Helly-based feature selection technique. HG AR-PNN was evaluated with respect to precision, recall, accuracy and stability. Arithmetic residue of the input feature vectors improves the stability of HG AR-PNN.