Network security risk assessment based on support vector machine

Author(s):  
Jun Chen ◽  
Xionggang Tu
2018 ◽  
Vol 232 ◽  
pp. 01043
Author(s):  
Haiyan Xie ◽  
Ying Wang ◽  
Xianghong Zhang

This paper establishes an information security evaluation model based on support vector machine by analyzing the factors affecting information security risk assessment. We compared and analyzed the different kernel functions of support vector machine by MATLAB, the experimental results show that the radial basis kernel function can minimize the training error and make the training result more accurate. Meanwhile, we compared the information security risk assessment based on support vector machine and BP neural network, the experimental results show the former has less error and shorter time. Therefore, the information security evaluation model based on support vector machine is feasible.


2011 ◽  
Vol 181-182 ◽  
pp. 799-803
Author(s):  
Yan Li Xu ◽  
Ling Ling Wang

to strengthen the network security and to enhance the accuracy of the network security risk assessment, the essay conducts game analysis to the security system of protective mechanisms. Using the basic theory of games and the analytical and comparative method, and raising the network security and physical model for the security system, this process will protect and improve the network security. At the aspect of setting the model, we did not rely on the traditional game theory, but creatively set behavior of the game for a large number of players for the limit logos of groups in the model, and paid more attention to the detection system to reach a state of stability. Analysis shows that the proposed models and the method are feasible and effective.


2010 ◽  
Vol 108-111 ◽  
pp. 948-953 ◽  
Author(s):  
Hao Yuan

Based on the research of domestic and foreign vulnerability assessment systems, in this paper, we propose an improved network security assessment method based on Immunity algorithm. It integrates the advantages of both host based and network based scan system. Our goal is to explore the known security vulnerabilities, and to check hosts’ security effectively as well. It has the features of self-adaptive, distributed, and real time. Therefore, it provides a good solution to risk assessment for network security.


Sign in / Sign up

Export Citation Format

Share Document