A Novel Intelligent Ensemble Classifier for Network Intrusion Detection System

The objective of this research paper is to propose a novel ensemble Intrusion Detection System (IDS) to classify intrusions. Network security is important and challenging, as there is a tremendous growth of network-based services and sensitive information shared on the network. Intrusion detection system (IDS) is a security mechanism used to detect, prevent unauthorized access to computer networks. IDS plays a vital role in maintaining the secure network. Therefore there is a need to develop reliable and robust IDS. Various data mining techniques are used to implement network intrusion detection. Recently, ensemble classifiers are used to implement it. A group of classifiers known as ensemble classifiers outperforms base classifiers. This paper deals with a novel ensemble classifier based on naive Bayes and ADTree for intrusion detection. ADTree is a well known supervised boosting decision tree algorithm. Naive bayes is a linear classifier and assumes that all features are independent. Naive Bayes will not perform well, where complex attribute dependencies are present. The proposed ensemble combines ADTree and Naive Bayes to improve classification accuracy of the detection system. Our experimental results show that the proposed ensemble classifier outperforms other classifiers in terms of accuracy.