基于灰色Verhulst的网络安全态势感知模型

A situation awareness model of network security based on grey Verhulst model

为了满足对抗性环境中对网络安全监测和预警的需要,提出了一种非等时距灰色Verhulst残差修正的安全态势感知模型.由非等时距的原始采样风险数据序列入手,根据累加序列所呈现出"S"形或反"S"形的摆动特征,选用灰色Verhulst模型或其反函数模型预测出网络未来的风险值,然后基于多级残差对模型的预测精度进行修正,最后应用修正后的新模型得到直观的网络未来安全态势曲线图.经过试验示例与仿真,表明该模型对网络安全态势的感知能够达到令人满意的拟合精度,具有实用价值.

To meet the need of the monitoring and early-warning to the safety of the network system within the oppositional environment, this paper proposed a situation awareness model for the network security based on the unequal interval grey Verhulst model with residual correction. Starting with the unequal interval original sampling risk data sequence, it selected the grey Verhulst model or its inverse function to forecast the future risk value of network based on the swaying character of S or reverse S shape presented by accumulated sequences. Through modifying the forecast precision of the model based on the multilevel residual error, the intuitionistic situation curve of the network security was obtained. Results of the experiment and simulation indicate that the presented model can achieve a satisfactory precision on situation awareness of the network security and can be used practically.