The Study of Information Security Risk Assessment Based on Support Vector Machine

摘要

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.