Computational Neural Network Regression Model for Host based Intrusion Detection System

Publication date: Available online 20 April 2016 Source:Perspectives in Science Author(s): Sunil Kumar Gautam, Hari Om In current scenario of information gathering and storing in secure system is challenging task due to increasing of cyber-attacks. There exists several computational neural network techniques designed for Intrusion Detection System which provide security to single machine and entire network's machine. In this paper, we have used two types of computational neural network models namely, Generalized Regression Neural Network (GRNN) model and Multilayer Perceptron Neural Network (MPNN) model for Host based Intrusion Detection System using log-files which are generated by a single personal computer. The simulation results show correctly classified percentage of normal and abnormal (intrusion) class using confusion matrix. On the basis of results and discussion, we found that, the Host based Intrusion Systems Model (HISM) significantly improved the detection accuracy while retaining minimum false alarm rate.

Source: Perspectives in Science - April 20, 2016 Category: Science Source Type: research