Association Rule-Mining-Based Intrusion Detection System With Entropy-Based Feature Selection

Abstract

Intrusion detection system (IDSs) are important to industries and organizations to solve the problems of networks, and various classifiers are used to classify the activity as malicious or normal. Today, the security has become a decisive part of any industrial and organizational information system. This chapter demonstrates an association rule-mining algorithm for detecting various network intrusions. The KDD dataset is used for experimentation. There are three input features classified as basic features, content features, and traffic features. There are several attacks are present in the dataset which are classified into Denial of Service (DoS), Probe, Remote to Local (R2L), and User to Root (U2R). The proposed method gives significant improvement in the detection rates compared with other methods. Association rule mining algorithm is proposed to evaluate the KDD dataset and dynamic data to improve the efficiency, reduce the false positive rate (FPR) and provides less time for processing.