Intrusion Detection and Prevention in Networks Using Machine Learning and Deep Learning Approaches: A Review

Abstract

As network services are used more and more, security is considered one of the main and important concerns of the network. Many computers connected to the network play important roles in business and other applications that provide services over the network. Thus we must seek out the most effective ways to safeguard the system. The Intrusion Detection System (IDS) is one of the most important information security technologies that use machine learning and deep learning algorithms to detect network anomalies. The accuracy of an intrusion detection system determines its performance. To reduce false alarms and increase detection rates, intrusion detection accuracy must be improved. The main function of an intrusion detection system is to analyze huge amounts of network traffic data. The main objective of this paper is to survey in-depth learning and machine learning methods for intrusion detection by reviewing literature and providing background information on either deep learning or machine learning algorithms on intrusion detection systems. The study also includes a performance comparison of different machine learning classification methods on the DARPA dataset.