Research on the Detection Method of the Malicious Attacks on Campus Network

Abstract:

The problem of malicious attacks detection on campus network is studied to improve the accuracy of detection. When detecting malicious attacks on campus network, a conventional manner is usually conducted in malicious attack detection of campus network. If a malicious signature is mutated into a new feature, the conventional detection method cannot recognize the new malicious signature, resulting in a relative low detection accuracy rate of malicious attacks. To avoid these problems, in this paper, the malicious attacks detection method for campus network based on support vector machine algorithm is proposed. The plane of support vector machine classification is constructed, to complete the malicious attacks detection of campus network. Experiments show that this approach can improve the accuracy rate of the malicious attack detection, and achieve satisfactory results.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 3291-3294
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.3291
• Online since: September 2014
• Authors: Jing Lei Wang*
• Keywords: Campus Network, Malicious Attacks, Support Vector Machine (SVM)

References

[1] D. Subhadrabandhu, F. Anjum, and S. Sarkar. On optimal placement of intrusion detection modules in sensor networks[C]. Proceedings of the First International Conference on Broadband Networks, 2004: 690-699.

DOI: 10.1109/broadnets.2004.52

[2] Anjum F, Subhadrabandhu D, Sarkar S, et al. On Optimal Placement of Intrusion Detection Modules in Sensor Networks[C]. 1st International Conference on Broadband Networks. Washington: IEEE Press, 2004: 433–439.

DOI: 10.1109/broadnets.2004.52

[3] O. Chapelle,V. Vapnik. Choosing multiple parameters for support vector machines. [J] Machine Learning，2002，46：131-159.

[4] Bi Changjian. Modeling and Simulation are Geared to Challenge in the Age of Big Data[J]. Compution Simulation, 2014, 1(31): 1-3.

[5] Wang Zhongcai, Li Yongbi. Intrusion Detection System Based on Data Mining Research [J]. Bulletin of Science and Technology, 2012, 28(8): 150-152.

[6] Dai Tianhong, Wang Keqi, Yang Shaochun. Intrusion Detection Research Based on Support Vector Machine [J]. China safety science journal, 2008, 18(4): 126-130.