Intrusion Detection based on a Novel Hybrid Learning Approach

Abstract

Information security and Intrusion Detection System (IDS) plays a critical role in the Internet. IDS is an essential tool for detecting different kinds of attacks in a network and maintaining data integrity, confidentiality and system availability against possible threats. In this paper, a hybrid approach towards achieving high performance is proposed. In fact, the important goal of this paper is generating an efficient training dataset. To exploit the strength of clustering and feature selection, an intensive focus on intrusion detection combines the two, so the proposed method is using these techniques too. At first, a new training dataset is created by K-Medoids clustering and Selecting Feature using SVM method. After that, Naïve Bayes classifier is used for evaluating. The proposed method is compared with another mentioned hybrid algorithm and also 10-fold cross validation. Experimental results based on KDD CUP'99 dataset show that the proposed method has better accuracy, detection rate and also false alarm rate than others.