By Topic

An Artificial Immune System Based on Holland's Classifier as Network Intrusion Detection

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Arisoa S. Randrianasolo ; Sch. of Comput. & Inf., Lipscomb Univ., Nashville, TN, USA ; Larry D. Pyeatt

In this paper, an Artificial Immune System based on Hollandâs Classifier is proposed as a new method for network intrusion detection. This paper is not aimed to provide a comparative study but to give more understanding on the feasibility of combining Artificial Immune System and Hollandâs Classifier to detect network intrusion. This new Artificial Immune System, named AIS-CS, can attain higher than 90% intrusion detection with a false negative percentage below 10% and a fairly low false positive rate on a network composed of 50 regular nodes and 50 intruders. The experiments appear to suggest that the best performance can be found by setting the tolerization and the simulation parameters differently. Since there are numerous parameters involved, more experiments need to be performed to further measure this Holland classifier based Artificial Immune System.

Published in:

Machine Learning and Applications (ICMLA), 2012 11th International Conference on  (Volume:1 )

Date of Conference:

12-15 Dec. 2012