COMPARATIVE EVALUATION OF MACHINE LEARNING METHODS FOR NETWORK INTRUSION DETECTION SYSTEM

Abstract

Cyber security is becoming more sophisticated, and as a result, there is an increasing challenge to accurately detect intrusions. Lack of intrusion prevention can degrade the credibility of security services, namely data confidentiality, integrity and availability. Many intrusion detection methods have been suggested in the literature to address threats to computer security, which can be broadly classified into signature-based intrusion detection (SIDS) and anomaly-based intrusion detection systems. (AIDS). This research presents the contemporary taxonomy of IDS, a comprehensive review of important recent work, and an overview of commonly used datasets for assessment purposes. It also presents detail analysis of different machine learning approach for intrusion detection.