基于粗粒化处理的计算机网络安全态势预测研究

Research on Computer Network Security Situation Prediction Based on Coarse Graining Processing

计算机网络中的用户类型复杂,在运行中容易遭到各种攻击,为了准确预测计算机网络的安全态势,提出了基于粗粒化处理的计算机网络安全态势预测研究。根据网络服务和网络主机的威胁系数,计算网络的威胁系数,通过将威胁系数转换成网络符号片段,对计算机网络的安全态势进行粗粒化处理。在网络安全态势的状态集合内,将计算机网络的历史态势和将来态势作为影响其安全运行的因素,通过计算不同防御状态在计算机网络中的概率分配情况,确定不同防御状态的可信度区间,实现计算机网络安全态势的预测。实验结果表明,文中方法能够避免安全态势时间序列之间的较大跨度影响预测结果,并将预测精度提高到90%以上,保证网络的安全性。

The types of users in computer networks are complex,and they are vulnerable to various attacks in operation.In order to accurately predict the security situation of computer networks,a research on computer network security situation prediction based on coarse-grained processing is proposed.According to the threat coefficient of network service and network host,the threat coefficient of network is calculated,and the security situation of computer network is coarsened by converting the threat coefficient into network symbol fragments.In the state set of network security situation,the historical situation and future situation of computer network are taken as the factors that affect its safe operation.By calculating the probability distribution of different defense states in computer network,the credibility interval of different defense states is determined,and the prediction of computer network security situation is realized.The experimental results show that the proposed method can avoid the large span between security situation time series from affecting the prediction results,improve the prediction accuracy to over 90%,and ensure the security of the network.