一种局部时空图卷积方法及其在网络漏洞预测的应用

A local spatio-temporal graph convolution-based approach and its application to network vulnerability prediction

针对网络安全态势预测中时空特征提取的不足,提出了一种基于局部时空卷积的网络漏洞预测方法,即局部时空图卷积网络模型,并针对网络漏洞数据选取历史平均法、长短期记忆网络、支持向量回归、时空图卷积网络模型进行对比实验。实验结果表明,提出的局部时空图卷积网络模型能够有效提高预测漏洞的时间、位置以及网络漏洞类型的准确度。

To address the shortage of spatio-temporal feature extraction in network security situation prediction,a local spatiotemporal convolution-based network vulnerability prediction method,namely the local spatio-temporal graph convolutional network model,is proposed,and HA,LSTM,SVR and STGCN models are selected for comparison experiments on network vulnerability data.Experimental results show that the model proposed in this paper can effectively improve the accuracy in predicting the time and location of vulnerabilities as well as the type of network vulnerabilities.