An Efficient Random Iterative Based Particle Swarm Optimization for Intrusion Detection
Sonal M. Wange1, Shiv K. Sahu2, Amit Mishra3
1Sonal M. Wange, Technocrats Institute of Technology, Bhopal (M.P), India.
2Dr. Shiv K. Sahu, Technocrats Institute of Technology, Bhopal. (M.P), India.
3Prof. Amit Mishra, Technocrats Institute of Technology, Bhopal (M.P), India.
Manuscript received on 15 June 2016 | Revised Manuscript received on 25 June 2016 | Manuscript Published on 30 June 2016 | PP: 10-14 | Volume-6 Issue-1, June 2016 | Retrieval Number: A2315066116/16©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 intrusion classification has been proposed by the help of association rule and random iterative based particle swarm optimization NSL-KDD dataset has been used for the experimentation. This is done by the separation of nodes by receiving and sending. Then it is examined for malicious behavior. RIPSO is applied then to examine the approved threshold value for the detection of different intrusion types defined. If the value obtained after RIPSO iteration passed the threshold assigned, then it will be categorized as the specific intrusion and type will identified. Denial of Service (DoS), User to Root (U2R), Remote to User (R2L) and Probing (Probe) attacks is considered in this paper for intrusion detection. The results show the improvement in detection as compared to the previous method. The average accuracy obtained by our approach is 91.3 %.Index.
Keywords: RIPSO, Intrusion Detection, DoS, U2R, R2L and Probe.
Scope of the Article: Cross-Layer Optimization