A Comparison of Different Machine Learning Algorithms for Intrusion Detection

Titre	A Comparison of Different Machine Learning Algorithms for Intrusion Detection
Publication Type	Journal Article
Year of Publication	2020
Authors	Karbal, B, Romadi, R
Journal	Communications in Computer and Information Science
Volume	1264
Pagination	157-169
Mots-clés	Anomaly detection, Classification (of information), Computer crime, Data communication systems, Data mining, Data mining algorithm, Deep learning, Intrusion detection, Intrusion Detection Systems, Learning algorithms, Learning systems, Machine learning techniques, Network anomaly detection, Network intrusion detection systems, Network security, Primary objective, Research problems, Security violations
Abstract	With the rapid development of the internet, intrusion detection became one of the major research problems in computer security. Many Intrusion Detection Systems (IDS) use data mining algorithms for classifying network traffic data and detecting different security violations. In this paper, we present some of the datasets and methods employed with the focus on network anomaly detection. We compare different machine learning techniques used in the latest research carried out for developing network intrusion detection systems. We also present an overview of some deep learning methodologies and their application for IDS purposes. The primary objective of this survey is to provide with a researcher, the state of the artwork already performed in this field of research. © 2020, Springer Nature Switzerland AG.
URL	https://www.scopus.com/inward/record.uri?eid=2-s2.0-85097408678&doi=10.1007%2f978-3-030-61143-9_13&partnerID=40&md5=3725b891261e386c6df84eebcbc0e514
DOI	10.1007/978-3-030-61143-9_13