Comparison of Supervised, Semi-supervised and Unsupervised Learning Methods in Network Intrusion Detection System (NIDS) Application

Authors

  • Nari Sivanandam Arunraj Technology Campus Grafenau, Deggendorf Institute of Technology
  • Robert Hable Technology Campus Grafenau, Deggendorf Institute of Technology
  • Michael Fernandes Technology Campus Grafenau, Deggendorf Institute of Technology
  • Karl Leidl Institute for Protection of Industrial Technology, Deggendorf Institute of Technology
  • Michael Heigl Institute for Protection of Industrial Technology, Deggendorf Institute of Technology

DOI:

https://doi.org/10.26034/lu.akwi.2017.3183

Abstract

With the emergence of the fourth industrial revolution (Industrie 4.0) of cyber physical systems, intrusion detection systems are highly necessary to detect industrial network attacks. Recently, the increase in application of specialized machine learning techniques is gaining critical attention in the intrusion detection community. A wide variety of learning techniques proposed for different network intrusion detection system (NIDS) problems can be roughly classified into three broad categories: supervised, semi-supervised and unsupervised. In this paper, a comparative study of selected learning methods from each of these three kinds is carried out. In order to assess these learning methods, they are subjected to investigate network traffic datasets from an Airplane Cabin Demonstrator. In addition to this, the imbalanced classes (normal and anomaly classes) that are present in the captured network traffic data is one of the most crucial issues to be taken into consideration. From this investigation, it has been identified that supervised learning methods (logistic and lasso logistic regression methods) perform better than other methods when historical data on former attacks are available. The performance of semi-supervised learning method (One class support vector machine) is comparatively better than supervised learning method (Isolation Forest) when historical data on former attacks are not available.

Downloads

Published

2017-11-20

Issue

Section

Fundamentals