Abstract  As the internet applications are growing rapidly, t he intrusions to the networking system are also bec oming high. In such a scenario, it is necessary to provide securit y to the networks by means of effective intrusion d etection and prevention methods. This can be achieved mainly by developing efficient intrusion detecting systems that use efficient algorithms which can identify the abnormal activities in the network traffic and protect the network resources from illegal penetrations by intruders. Though many intrusion detection systems have been proposed in the past, the existing network intrusion detections have limitations in terms of detection time and acc uracy. To overcome these drawbacks, we propose a ne w intrusion detection system in this paper by developing a new intelligen t Conditional Random Field (CRF) based feature sele ction algorithm to optimize the number of features. In addition, an ex isting Layered Approach (LA)  based algorithm is used to perform classification with these reduced features. This in trusion detection system provides high accuracy and achieves efficiency in attack detection compared to the existing approache s. The major advantages of this proposed system are reduction in detection time, increase in classification accuracy and reduction in false alarm rates.    

References

[1] Amiri F., Yousefi M., Lucas C., Shakery A., and Yazdani N., Mutual Information-Based Feature Selection for Intrusion Detection Systems, the Journal of Network and Computer Applications , vol. 34, no. 4, pp. 1184-1199, 2011.

[2] Bace R. and Mell P., Intrusion Detection Systems, Computer Security Division, Information Technology Laboratory , Nat l Inst. of Standards and Technology , 2001.

[3] Chimphlee W., Abdullah A., Sap M., Chimphlee S., and Srinoy S., A Rough-Fuzzy Hybrid Algorithm for Computer Intrusion Detection, the International Arab Journal of Information Technology , vol. 4, no. 3, pp. 247-254, 2007.

[4] Gupta K., Kotagiri R., and Nath B., Conditional Random Fields for Intrusion Detection, in Proceedings of the 21 st International Conference Advanced Information Networking and Applications Workshops , Niagara Falls, pp. 203- 208, 2007.

[5] Gupta K., Nath B., and Kotagiri R., Layered Approach using Conditional Random Fields for Intrusion Detection, IEEE Transactions on Dependable and Secure Computing , vol. 7, no.1, pp. 35-49, 2010.

[6] KDD Cup 1999 Intrusion Detection Data., available at: http://kdd.ics.uci.edu/databases/kddcup99/kddcu p99.html, last visited 2010.

[7] Lafferty J., Mccallum A., and Pereira F., Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data, in Proceedings of the 18 th International Conference Machine Learning , San Francisco, pp. 282-289, 2001.

[8] Li J., Wang H., and Yu J., Research on the Application of CRFs Based on Feature Sets in Network Intrusion Detection, in Proceedings of IEEE International Conference on Security Technology , Hainan Island, pp. 194-197, 2008. 50 The International Arab Journal of Information Techn ology

[9] Mccallum A. and Sutton C., An Introduction to Conditional Random Fields for Relational Learning, Introduction to Statistical Relational Learning , vol. 4, no. 4, pp. 267-373, 2006.

[10] Prema L. and Kannan A., An Active Rule Approach for Network Intrusion Detection with Enhanced C4.5 Algorithm, the Journal of Communications, Network and System Sciences , vol. 1, no. 4, pp. 314-321, 2008.

[11] Sindhu S., Geetha S., and Kannan A., Decision Tree Based Light Weight Intrusion Detection Using a Wrapper Approach, Expert Systems with Applications , vol. 39, no. 1, pp. 129-141, 2012.

[12] Wilk T. and Michal K., Soft Computing Methods Applied to Combination of One-class Classifiers, Neuro Computing , vol. 75, no. 1, pp. 185-193, 2012. Sannasi Ganapathy has completed Ms degree of computer applications from Madurai Kamaraj University in 2005, Ms degree of engineering in computer science and engineering from Anna University, Chennai in 2007. He received his PhD degree from Anna University, Chennai in 2013. He has published more than 20 papers in Journals and Conferences. He has more than 6 years of teaching experience in Engineering colleges. His areas of interest include data mining, network security, the ory of computation and artificial intelligence. Pandi Vijayakumar completed his PhD degree in computer science and engineering in Anna University Chennai in the year 2013. He Completed Ms degree of engineering in the field of Computer science and engineering in Karunya Institute of Technology affiliated to Anna University, in the ye ar 2005. He completed his Bachelor of engineering in Madurai Kamaraj University, Madurai in the year 2002. He is presently working as an Assistant Professor at Anna University Chennai (University College of Engineering, Tindivanam), Chennai, India . His main thrust research areas are Key management i n network security and multicasting in computer networks. Palanichamy Yogesh is working as an Associate Professor in the Department of Information Science and Technology, College of Engineering Guindy Campus, Anna University, Chennai, India. He possesses bachelor and Ms degrees in computer science and engineering from Madurai Kamaraj University, India. He received his PhD degr ee from Anna University, Chennai, India. He has 5 year s of experience in industry and 20 years of experienc e in academic and research. His areas of interests inclu de data communication networks, mobile computing, multimedia communication and wireless security. Currently, he is working in the areas of internet o f things and software defined networking. Arputharaj Kannan is working as an Professor and Head in the Department of Information Science and Technology, College of Engineering Guindy Campus, Anna University, Chennai, India. He possesses Ms degree in computer science and engineering from Anna University, Chennai, India. He received his PhD degree from Ann a University, Chennai, India. He has 8 years of experience in industry and 23 years of experience i n academic and research. His areas of interests inclu de data mining, networks security, software engineerin g and artificial intelligence. He has more than 185 publications in Journals and Conferences.