Feature selection using Rough-DPSO in anomaly intrusion detection

• Main Authors: Zainal, Anazida, Maarof, Mohd Aizaini, Shamsuddin, Siti Mariyam
• Format: Article
• Published: Springer-Verlag Berlin Heildelberg 2007
• Subjects: QA76 Computer software
• Online Access: http://eprints.utm.my/id/eprint/5599/; https://link.springer.com/chapter/10.1007/978-3-540-74472-6_42
• Institution: Universiti Teknologi Malaysia

Most of the existing IDS use all the features in network packet to evaluate and look for known intrusive patterns. Some of these features are irrelevant and redundant. The drawback to this approach is a lengthy detection process. In real-time environment this may degrade the performance of an IDS. Thus, feature selection is required to address this issue. In this paper, we use wrapper approach where we integrate Rough Set and Particle Swarm to form a 2-tier structure of feature selection process. Experimental results show that feature subset proposed by Rough-DPSO gives better representation of data and they are robust.