ABSTRACT

Network security technology has become crucial in protecting government and industry computing infrastructure. Due to the network attacks over the past few years the intrusion detection system (IDS) is increasingly becoming a crucial component to secure network. In recent years, data mining - based intrusion detection systems (IDSs) have demonstrated high accuracy, good generalization to novel types of intrusion, and robust behaviour in a changing environment. . Instrumenting components such as model deployment, data transformations, and cooperative distributed detection remain a labour intensive and complex engineering endeavour. In data mining based intrusion detection system we should have thorough knowledge about the particular domain in relation to intrusion detection so as to efficiently extract relative rule from huge amounts of records.  Modern intrusion detection applications face complex requirements - they need to be reliable, extensible, easy to manage, and have low maintenance cost. Still, significant challenges exist in design and implementation of production quality IDSs. This paper gives the classifier algorithm model for attack category and ensemble approach for detection.

KEYWORDS:  Data mining, Ensemble approach, Network intrusion detection system, classifier, network security, Algorithm selection.