A CLASSIFICATION MODEL WITH OPTIMIZATION BASED FEATURE SELECTION METHOD FOR INTRUSION DETECTION SYSTEM

Abstract

Securing a network from the attackers is a challenging task at present as users use different kinds of networks and variety of tasks.  To protect any individual host in a network or the entire network, some security system must be implemented.  In this case, the Intrusion Detection System (IDS) is a methodology which protects the network from the intruders.  The IDS deals with network packets with different characteristics.  A signature-based IDS is a potential tool to understand former attacks and to define suitable method to conquest it in variety of applications.  In this research work, a model is proposed which consists of two primary phases as (i) Feature Selection and (ii) Classification.  Since the length of feature vector tends to high, includes optimal feature selection technology, from which the most relevant features are selected by the Lion-based Firefly Algorithm which is referred as Optimization based Feature Selection Method (OFSM).  The main objective of this paper is projected on minimizing the correlation between the selected features, in which results with diverse information regarding the different classes of data are provided.  Once, the optimal features are selected, the classification algorithm called Neural Network (NN) is adopted, which can classify the data in an effective manner with the selected features.