An effective technique for intrusion detection using neuro-fuzzy and radial SVM classifier

Abstract

Intrusion detection is not yet a perfect technology. This has given data mining the opportunity to make several important contributions to the field of intrusion detection. In this paper, we have proposed a new technique by utilizing data mining techniques such as neuro-fuzzy and radial basis support vector machine (SVM) for the intrusion detection system. The proposed technique has four major steps in which, first step is to perform the Fuzzy C-means clustering (FCM). Then, neuro-fuzzy is trained, such that each of the data point is trained with the corresponding neuro-fuzzy classifier associated with the cluster. Subsequently, a vector for SVM classification is formed and in the fourth step, classification using radial SVM is performed to detect intrusion has happened or not. Data set used is the KDD cup 99 dataset and we have used sensitivity, specificity and accuracy as the evaluation metrics parameters. Our technique could achieve better accuracy for all types of intrusions. It achieved about 98.94 % accuracy in case of DOS attack and reached heights of 97.11 % accuracy in case of PROBE attack. In case of R2L and U2R attacks it has attained 97.78 and 97.80 % accuracy respectively. We compared the proposed technique with the other existing state of art techniques. These comparisons proved the effectiveness of our technique. © 2013 Springer Science+Business Media.