A Review on Machine Learning Based Intrusion Detection System: Techniques, Public Datasets and Challenges

This review paper focuses on the machine learning techniques used by the research community for detecting anomalies in network traffic in order to show intrusion activities.
The paper states some of the state-of-the-art machine learning techniques used in anomaly detection. Furthermore, the paper briefly describes the evolution of training datasets, highlights the main representatives, and points out some of the shortcomings that should be taken into consideration while addressing the issues of anomaly detection with intrusion detection systems in modern IT network environments. The review emphasizes the perspectives for future work on this subject by presenting the challenges of training machine learning models for anomaly detection in intrusion detection systems.