Comparative Study of Selected Data Mining Algorithms used for Intrusion Detection
Ajayi Adebowale1, Idowu S.A2, Anyaehie Amarachi A.3
1Ajayi Adebowale, Computer Science department, Babcock University, Ilishan, Nigeria.
2Idowu S.A, Computer Science department, Babcock University, Ilishan, Nigeria.
3Anyaehie Amarachi, Computer Science department, Babcock University, Ilishan, Nigeria.
Manuscript received on June 07, 2013. | Revised Manuscript received on June 29, 2013. | Manuscript published on July 05, 2013. | PP: 237-241 | Volume-3 Issue-3, July 2013. | Retrieval Number: C1662073313/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: 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 the relatively new field of data mining and intrusion detection a lot of techniques have been proposed by various research groups. Researchers continue to find ways of optimizing and enhancing the efficiency of data mining techniques for intrusion attack classification. This paper evaluates the performance of well known classification algorithms for attack classification. The focus is on five of the most popular data mining algorithms that have been applied to intrusion detection research; Decision trees, Naïve bayes, Artificial neural network, K-nearest neighbor algorithm and Support vector machines. We discuss their advantages and disadvantages and finally we induce the NSL-KDD dataset with the respective algorithms to see how they perform.
Keywords: Data mining, Intrusion detection, decision trees, Naive bayes, Artificial neural network, k-nearest neighbor, Support vector Machines, NSL-KDD