An Integrated Intrusion Detection System by Combining SVM with AdaBoost

Yu Ren

College of Computer, Communication University of China, Beijing, China.

DOI: 10.4236/jsea.2014.712090                

Abstract

In the Internet, computers and network equipments are threatened by malicious intrusion, which seriously affects the security of the network. Intrusion behavior has the characteristics of fast upgrade, strong concealment and randomness, so that traditional methods of intrusion detection system (IDS) are difficult to prevent the attacks effectively. In this paper, an integrated network intrusion detection algorithm by combining support vector machine (SVM) with AdaBoost was presented. The SVM is used to construct base classifiers, and the AdaBoost is used for training these learning modules and generating the final intrusion detection model by iterating to update the weight of samples and detection model, until the number of iterations or the accuracy of detection model achieves target setting. The effectiveness of the proposed IDS is evaluated using DARPA99 datasets. Accuracy, a criterion, is used to evaluate the detection performance of the proposed IDS. Experimental results show that it achieves better performance when compared with two state-of-the-art IDS.

Keywords

Intrusion Detection, Integrated Learning, Support Vector Machine, AdaBoost

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Xiao, L., Chen, Y. and Chang, C.K. (2014) Bayesian Model Averaging of Bayesian Network Classifiers for Intrusion Detection. Proceedings of the 2014 IEEE 38th Annual International Computers, Software and Applications Conference Workshops, Vasteras, 2014, 128-133.
[2]	Panja, B., Ogunyanwo, O. and Meharia, P. (2014) Training of Intelligent Intrusion Detection System using Neuro Fuzzy. Proceedings of 2014 15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), Las Vegas, 2014, 1-6.
[3]	Fuchsberger, A. (2005) Intrusion Detection System and Intrusion Prevention Systems. Information Security Technical Report, 34, 134-139. http://dx.doi.org/10.1016/j.istr.2005.08.001
[4]	Larranaga, P., Karshenas, H. and Bielza, C. (2013) A Review on Evolutionary Algorithms in Bayesian Network Learning and Inference Tasks. Information Sciences, 233, 109-125 http://dx.doi.org/10.1016/j.ins.2012.12.051
[5]	Wang, Z., Li, L. and Niu, L. (2009) Load Modeling Based on Support Vector Machine Based on Bayesian Evidence Framework. Transactions of China Electrotechnical Society, 24, 83-86.
[6]	Davy, M., Desobry, F. and Arthur, G. (2006) An Online Support Vector Machine for Abnormal Events Detection. Signal Processing, 86, 2009-2025. http://dx.doi.org/10.1016/j.sigpro.2005.09.027
[7]	Wang, Z. and Sun, X. (2011) Document Classification Algorithm Based on MMP and LS-SVM. Procedia Engineering, 15, 1565-1569. http://dx.doi.org/10.1016/j.proeng.2011.08.291
[8]	Li, M., Wen, G. and Wang, S. (2008) Parameters Selection of Support Vector Regression Based on Genetic Algorithm. Computer Engineering and Applications, 44, 23-26.
[9]	Yang, G., Li, C. and Ma, G. (2008) Parameter Selection for Support Vector Machines Based on Hybrid Genetic Algorithm. Journal of Harbin Institute of Technology, 40, 134-138.
[10]	Chen, A., Xia, L. and Zhao, G. (2004) Face Detection Based on Boosting Algorithm. Computer Engineering and Applications, 27, 48-52.
[11]	Fei, W., Zhuang, Y. and Pan, H. (2003) Recognition of Multiple Audio Clip Classes Based on FBM and AdaBoosting. Journal of Computer Research and Development, 18, 62-65.
[12]	Zhao, J. (2013) Asymptotic Convergence of Dimension Reduction Based Boosting in Classification. Journal of Statistical Planning and Inference, 143, 651-662. http://dx.doi.org/10.1016/j.jspi.2012.10.007
[13]	Xia, L. and Dai, R. (2003) Fault Testing on Rolling Bearing Based on Boosting Fuzzy Classification. Pattern Recognition and Artificial Intelligence, 18, 72-75.