Classifying the Network Intrusion Attacks using Data Mining Classification Methods and their Performance Comparison

Security is becoming a critical part of organizational information systems. Intrusion Detection System (IDS) is an important detection that is used as a countermeasure to preserve data integrity and system availability from attacks. The main reason for using Data Mining Classification Methods for Intrusion Detection Systems is due to the enormous volume of existing and newly appearing network data that require processing. In this paper we are using CART [1] [4], Naïve Bayesian [2] [10], and Artificial Neural Network Model [3] [10], data mining classification methods. These are proving to be useful for gathering different knowledge for Intrusion Detection. This paper presents the idea of applying data mining classification techniques to intrusion detection systems to maximize the effectiveness in identifying attacks, thereby helping the users to construct more secure information systems.