Advertisement
Published in:
2020 | OriginalPaper | Chapter
A Detailed Analysis of Using Supervised Machine Learning for Intrusion Detection
Authors : Ahmed Ahmim, Mohamed Amine Ferrag, Leandros Maglaras, Makhlouf Derdour, Helge Janicke
Published in: Strategic Innovative Marketing and Tourism
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Machine learning is more and more used in various fields of the industry, which go from the self driving car to the computer security. Nowadays, with the huge network traffic, machine learning represents the miracle solution to deal with network traffic analysis and intrusion detection problems. Intrusion Detection Systems can be used as a part of a holistic security framework in different critical sectors like oil and gas industry, traffic management, water sewage, transportation, tourism and digital infrastructure. In this paper, we provide a comparative study between twelve supervised machine learning methods. This comparative study aims to exhibit the best machine learning methods relative to the classification of network traffic in specific type of attack or benign traffic, category of attack or benign traffic and attack or benign. CICIDS’2017 is used as data-set to perform our experiments, with Random Forest, Jrip, J48 showing better performance.