Universiti Teknologi Malaysia Institutional Repository

Class specific features for attacks in network intrusion detection system

Zainal, Anazida and Maarof, Mohd. Aizaini and Shamsuddin, Siti Mariyam (2008) Class specific features for attacks in network intrusion detection system. Jurnal Teknologi Maklumat, 20 (3). pp. 14-27. ISSN 0128-3790

[img]
Preview
PDF - Published Version
566Kb

Abstract

Most of the existing Intrusion Detection System (IDS) uses all the features to determine whether an input does have an intrusive pattern or otherwise. Some of these features are redundant and some have little contribution to the detection process. The purpose of this study is to identify small number of significant features that can represent most of the attack types. Here, we used Kohonen SOM to classify the input data into their respective attack categories. Empirical results indicate that generic feature subset previously obtained is not suitable to represent all the attack categories. Instead, different categories of attacks best represented using different significant feature subset.

Item Type:Article
Uncontrolled Keywords:intrusion detection system, feature selection, class specific features, classification and kohonen SOM
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:10691
Deposited By: Ms Zalinda Shuratman
Deposited On:22 Oct 2010 05:01
Last Modified:22 Oct 2010 05:01

Repository Staff Only: item control page