Prediction of Networks Security Situation Based on Wavelet Kernel Function Network

Abstract:

Based on the foundation of prediction of networks security situation models, this article proposed a method about applying wavelet kernel function network to prediction of networks security situation. Wavelet kernel function network combined with the neural network and the support vector machines merits, which avoid support vector machine (SVM) solving binding second convex programming problem, network scale doesn't happen dimension disasters problem because kernel function is introduced, and its solution is the global optimal solution, so the situation prediction is more accurate. The experiment tests indicated that this method can accurately acquire the situation value prediction results, it has the good situation prediction potency, which provided one new key for prediction of networks security situation.

• Periodical: Applied Mechanics and Materials (Volume 127)
• Pages: 53-58
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.127.53
• Online since: October 2011
• Authors: Jian Qiong Xiao
• Keywords: Networks Security Situation, Prediction of Situational Value, Situation Assessment, Support Vector Machine (SVM), Wavelet Kernel Function Network

References

[1] MAGNUS A, LINQVIST D, ERLAND J. A multi-sensor model to improve automated attack detection[C]/Proc of the 11th International Symposium on Recent Advances in Intrusion Detection. (2008).

[2] AMBROSIO D, TAKIKAWA M, UPPER D, et al. Security situation assessment and response evaluation(SSARE)[C] /Proc of the DARPA Information Survivability Conference&Exposition. 2001: 387-394.

DOI: 10.1109/discex.2001.932233

[3] DENG Ju-Long. Grey prediction and making [M]. Huazhong University of science and technology press, (1986).

[4] YEGNESWARAN V, BARFORD P, PAXSON V. Using honey nets for Internet situational awareness[C] /Proc of the 4th Workshop on Hot Topics in Networks. (2005).

[5] REN Wei, JIANG Xing-hao, SUN Tan-feng. RBFNN-based Prediction of Networks Security Situation[J]. Computer Engineering and Application. 2006. 31.

[6] ZHANG Li, ZHOU Wei-Da, JIAO Li-Cheng. WAVELET KERNEL FUNCTION NETWORK, J. Infrared Millim. Waves, June, (2001).

[7] SUN Kai, WANG Ying-long. Research on Construction of Mercer Kernel Function in Support Vector Machine[J]. Advanced Manufacture and Management 2008, Vol. 27, No. 11.

[8] WANG Guo-Shen. Properties and Construction Methods of Kernel in Support Vector Machine[J]. Computer science. June, (2006).

[9] WEI Yong, LianYi-Feng. Based on the log audit and performance correction algorithm of network security situation assessment model [J]. Computer journal, April, 2009, 4: 763-772.

[10] XU Jian-Hua, ZHANG Xue-Gong, LI Yan-Da. A method based on the nonlinear perceptron algorithm of kernel function. [J]. Computer journal, 2002, 25(7).

[11] LIU Jian-wei, SHEN Fang-lin, LUO Xiong-lin. Reserch on Perceptron Learning Algorithm[J]. Computer Engineering, April (2010).

[12] YAN Gen-ting, MA Guang-fu, XIAO Yu-zhi. Support vectormachines based on hybrid kernel function. JOURNAL OF HARBIN INSTITUTE OF TECHNOLOGY. Nov. (2007).

[13] SAHofmeyr, S Forrest. Architecture for an artificial immune system[J]. Evolutionary Computation, 2000, 8(4): 443-473 Fig. 3 Security situation of host and server r^t(h)host r^t(h)net 0. 4 0. 2 0. 6 Fig. 2 Network security prediction 0 0. 05 0. 1 0. 15 0. 2 0. 25 1 2 3 4 5 6 7 8 predicted value effective value … outputlayer implicit layer input layer Wm W1 W2 x f(x) … K(x, x1) K(x, x2) … K(x, xm) ∑ Fig. 1 The Structure of Wavelet Kernel Function Network.