An Efficient Intrusion Detection System based on Random-Iteration Particle Swarm Optimization
Nidhi Shrivastava1, Ruchi Jain2, Shiv Kumar3
1Nidhi Shrivastava, M.Tech Student, Department of CTA, Lakshmi Narain College of Technology Excellence, Bhopal (M.P), India.
2Ruchi Jain, Assistant Professor, Department of Computer Science & Engineering, Lakshmi Narain College of Technology Excellence, Bhopal (M.P), India.
3Dr. Shiv Kumar, Professor, Department of Computer Science & Engineering, Lakshmi Narain College of Technology Excellence, Bhopal (M.P), India.
Manuscript received on 13 June 2017 | Revised Manuscript received on 20 June 2017 | Manuscript Published on 30 June 2017 | PP: 149-154 | Volume-6 Issue-5, June 2017 | Retrieval Number: E5025066517/17©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper an efficient framework has been developed for efficient intrusion detection system. In the first step the data NSL-KDD cup99 is divided into k-clusters based on the filtration parameters that are content feature, traffic features and the host feature. The clusters are separated based on the support value. Then random-iteration particle swarm optimization (RIPSO) has been applied on the cluster for the further data classification. The classification is considered for denial of service (DoS), user to root (U2R), remote to user (R2L) and probe attacks. The results are efficient in comparison to the previous methods.
Keywords: Association Rule Mining, RIPSO, DoS, U2R, R2L, Probe
Scope of the Article: Data Mining