An Intelligent Intrusion Detection System for Mobile Ad-Hoc Networks Using Classification Techniques

* Final gross prices may vary according to local VAT.

Get Access

Abstract

This paper proposes an intelligent multi level classification technique for effective intrusion detection in Mobile Ad-hoc Networks. The algorithm uses a combination of a tree classifier which uses a labeled training data and an Enhanced Multiclass SVM algorithm. Moreover, an effective preprocessing technique has been proposed and implemented in this work in order to improve the detection accuracy and to reduce the processing time. From the experiments carried out in this work, it has been observed that significant improvement has been achieved in this model from the view point of both high detection rates as well as low false alarm rates.