A detailed analysis of using supervised machine learning for intrusion detection

Document Type

Conference Proceeding

Publication Title

Strategic Innovative Marketing and Tourism

Publisher

Springer

School

School of Science

RAS ID

44685

Comments

Ahmim, A., Ferrag, M. A., Maglaras, L., Derdour, M., & Janicke, H. (2020). A detailed analysis of using supervised machine learning for intrusion detection. In Strategic Innovative Marketing and Tourism (pp. 629-639). Springer, Cham. https://doi.org/10.1007/978-3-030-36126-6_70

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.

DOI

10.1007/978-3-030-36126-6_70

Access Rights

subscription content

Link to Full Text

Share

 
COinS