Research on Property and Model Optimization of Multiclass SVM for NIDS

Abstract:

By investigating insufficiency of typical artificial intelligence algorithms aiming at the high rate of False-Positives and False-Negatives in the Intrusion Detection Systems (IDS), this paper presents an approach that Support Vector Machine (SVM) is embedded in Network Intrusion Detection System (NIDS). At the same time, by using online data and K-fold cross-validation method, this paper proposes a method to optimize the attributes and model of SVM respectively. Experimental results show that by using this method as the detection core of the intrusion detection system, the rate of False-Negatives in IDS can be reduced significantly.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 3696-3701
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.3696
• Online since: August 2013
• Authors: Jian Hao Song, Gang Zhao, Jun Yi Song
• Keywords: IDS, Online Detection, Rate of False-Negatives, Rate of False-Positives, Support Vector Machine (SVM)

References

[1] Vapnik V. The Nature of Statistical Learning Theory [M]. New York: Springer- Verlag, (1995).

[2] LI Hui, GUAN Xiao-Hong, ZAN Xin, and HAN Chong-Zhao, Network Intrusion Detection Based on Support Vector Machine[J], JOURNAL OF COMPUTER RESEARCH AND DEVELOPMENT, no. 40, (2003).

[3] Xiao Yun, Wang Xuanhong. Support Vector Machine theory and its application in network security. Xi'an Electronic and Science University Publishing House, (2011).

[4] LIU Xin-zhe, Application of artificial intelligence techniques to Intrusion Detection System [J]. Railway Computer Application, no. 08, (2004).

[5] RAO Xian, DONG Chun-xi , YANG Shao-quan, Detecting intrusions by using support vector machines [J] JOURNAL OF XIDIAN UNIVERSITY, no. 03, (2003).

[6] Guo Chi Chen Zhuo, Research of an Intrusion Detection Model Based on Support Vector Machine [J], Computer&Digital Engineering , no. 09, (2010).