Comparison of Machine Learning algorithms performance in detecting network intrusion

Abstract

Organization has come to realize that network security technology has become very important in protecting its information. With tremendous growth of internet, attack cases are increasing each day along with the modern attack method. One of the solutions to this problem is by using Intrusion Detection System (IDS). Machine Learning is one of the methods used in the IDS. In recent years, Machine Learning Intrusion Detection system has been giving high accuracy and good detection on novel attacks. In this paper the performance of a Machine Learning algorithm called Decision Tree (J48) is evaluated and compared with two other Machine Learning algorithms namely Neural Network and Support Vector Machines which has been conducted by A. Osareh [1] for detecting intrusion. The algorithms were tested based on accuracy, detection rate, false alarm rate and accuracy of four categories of attacks. From the experiments conducted, it was found that the Decision tree (J48) algorithm outperformed the other two algorithms.