Study on Genetic Algorithm Optimization for Support Vector Machine in Network Intrusion Detection

Abstract This paper studies on methods taken in solving the existing network disorders in network intrusion detection. Traditional parameter-optimized Support Vector Machine (SVM) may easily generate improper parameter-selections, and may further lead to a low accuracy in network intrusion detection. In order to overcome such problems, so well as to ensure the network security, this paper tries to put forward with a Genetic Algorithm optimized Support Vector Machine in network intrusion detection. For this purpose, some procedures have to be taken. Firstly the network intrusion data should be normalized and simplified for inputs, and then to obtain optimal parameters through the parameteroptimization for SVM with a Genetic Algorithm; Finally to get network intrusion results through detecting the network data normalized by an optimal Support Vector Machine (SVM) model. The simulating results show that, compared with the traditional network intrusion detection methods, the optimized Support Vector Machine (SVM) model with a Genetic Algorithm has a high accuracy, and a low rate of losing or false alarms, and is proved to be effective in network intrusion detection.

[1]  Wei Hu,et al.  AdaBoost-Based Algorithm for Network Intrusion Detection , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Nicolaos B. Karayiannis,et al.  Reformulated radial basis neural networks trained by gradient descent , 1999, IEEE Trans. Neural Networks.

[3]  Chih-Ming Chen,et al.  A self-organizing HCMAC neural-network classifier , 2003, IEEE Trans. Neural Networks.

[4]  Narasimhan Sundararajan,et al.  A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation , 2005, IEEE Transactions on Neural Networks.

[5]  Shai Ben-David,et al.  Learning Distributions by Their Density Levels: A Paradigm for Learning without a Teacher , 1997, J. Comput. Syst. Sci..

[6]  Wei Zhang,et al.  A genetic clustering method for intrusion detection , 2004, Pattern Recognit..

[7]  J Timmis,et al.  An artificial immune system for data analysis. , 2000, Bio Systems.

[8]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[9]  Guang-Bin Huang,et al.  Neuron selection for RBF neural network classifier based on data structure preserving criterion , 2005, IEEE Transactions on Neural Networks.

[10]  Xue Xu,et al.  Affine Alignment of Manifold , 2011 .

[11]  Kenneth Rose,et al.  A global optimization technique for statistical classifier design , 1996, IEEE Trans. Signal Process..

[12]  Bernhard Schölkopf,et al.  Support Vector Method for Novelty Detection , 1999, NIPS.

[13]  S. T. Sarasamma,et al.  Hierarchical Kohonenen net for anomaly detection in network security , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  ZHONGJiang,et al.  A Novel Dynamic Clustering Algorithm Based on Immune Network and Tabu Search , 2005 .

[15]  Don R. Hush,et al.  A Classification Framework for Anomaly Detection , 2005, J. Mach. Learn. Res..

[16]  Yue Wu,et al.  Analysis and Design of Scalable DRM in VOD , 2011 .

[17]  Shie-Jue Lee,et al.  An ART-based construction of RBF networks , 2002, IEEE Trans. Neural Networks.

[18]  Héctor Pomares,et al.  Multiobjective evolutionary optimization of the size, shape, and position parameters of radial basis function networks for function approximation , 2003, IEEE Trans. Neural Networks.

[19]  Salvatore J. Stolfo,et al.  Using artificial anomalies to detect unknown and known network intrusions , 2003, Knowledge and Information Systems.