Intrusion Detection System using Machine Learning Techniques: A Review

Abstract

The rapid growth in the use of computer networks results in the issues of maintaining the network availability, integrity, and confidentiality. This necessitates the network administrators to adopt various types of intrusion detection systems (IDS) that help in monitoring the network traffics for unauthorized and malicious activities. Intrusion is the breach of security policy with malicious intent. Therefore, intrusion detection system monitors traffic flowing on a network through computer systems to search for malicious activities and known threats, sending up alerts when it finds those threats. The detection of malicious activities is of two types, the misuse or signature-based detection in which the IDS collects information, analyzes it and then compares it to the attack signatures stored in a large database. The second detection is the anomaly detection which assumes malicious activity as any action that deviates from normal behavior. The proposed paper presents an overview of various works being done on building an efficient IDS using single, hybrid and ensemble machine learning (ML) classifiers, evaluated using seven different datasets. The results obtained by various works were discussed and compared which gives a clear path and guide for future work.