International Journal of Engineering and Information Systems (IJEAIS)   Year: 2022 | Volume: 6 | Issue: 2 | Page No.: 103-119 Evaluating Performance of Supervised Learning Techniques for Developing Real-Time Intrusion Detection System Download PDF Shadi I. Abudalfa, Ekhlas S. Isleem, Marah J. Elshaikh Khalil, Rewaa A. Dalloul and Shaimaa M. Iqtefan Abstract: Nowadays, a lot of organizations are currently suffering from serious security threats. Those threats often keep changing and may evolve to new, dangerous, and unknown types. Thereby, such organizations suffer from a business problem that consumes a huge cost for detecting a tremendous number of threats. For tackling this problem, intrusion detection systems have been presented to automatically detect security threats. Some of these systems use machine learning techniques for provides high accuracy with detecting new attacks. In this paper, we focus on developing intrusion detection system that uses supervised learning technique. The performance of several machine learning techniques were evaluated for highlighting the best technique that can be used for implementing intrusion detection systems. As a result of this work, a comparison framework has been provided by using public dataset. The techniques were evaluated by measuring classification Accuracy, Recall, Precision and F1-Score with different categories of attacks. The experimental results show that the highest accuracy is about 96.974% with using Decision Tree (DT) technique.