Pritam Sapate and Shital A. Raut, VNIT, India

Intrusion detection is the most essential component in network security. Traditional Intrusion Detection methods are based on extensive knowledge of signatures of known attacks. Signature-based methods require manual encoding of attacks by human experts. Data mining is one of the techniques applied to Intrusion Detection that provides higher automation capabilities than signature-based methods. Data mining techniques such as classification, clustering and association rules are used in intrusion detection. In this paper, we present an overview of intrusion detection, KDD Cup 1999 dataset and detailed analysis of different classification techniques namely Support vector Machine, Decision tree, Naïve Bayes and Neural Networks used in intrusion detection.

Intrusion Detection, Data Mining, KDD Cup 1999, Classification.