A Comparative Analysis of Different Classification Techniques for Intrusion Detection System

Abstract

Intrusion Detection Systems are the network security mechanism that monitors network and system activities for malicious actions. It becomes indispensable tool to keep information system safe and reliable. The primary goal of intrusion detection is to model usual application behaviour, so that we can recognize attacks by their peculiar effects without raising too many false alarms. In this work data mining techniques are used for intrusion detection to identify normal and malicious actions on the system. The whole work considered Intrusion detection as a data analysis process. The Weka tool is used for analysis on KDD Cup [1] dataset. Algorithm REPTree & VFI(Voting Feature Interval) are chosen in this work with full training set and percentage split in which dataset can be divided into two ratio, and then one part is used as training set and the other part is applied as test set. The ROC curve is implemented for the comparison of classification algorithms.