Evaluation of Network Security Grade Protection Combined With Deep Learning for Intrusion Detection

Using deep learning models, we predict information system security indicators and obtain corresponding security evaluation scores. The scores of these predicted security evaluation are used as the input data of regression tree model, and the security grade protection evaluation system is constructed. The model training process involves four different models: VGG19, ResNet-50, XceptionNet, and EfficientNet. Based on the training results, we find that the EfficientNet model consumes fewer computational resources in single detection while achieves a detection accuracy of 99.93%. Subsequently, we apply the CART regression tree to assess the network security posture of 14 commercial systems. The test results of the model show that the mean absolute percentage error(MAPE) is 0.029 and the correlation coefficient is 0.9. These empirical results strongly support the performance of the proposed model and show its significant potential in improving security assessments. With these training results, we gain preliminary insights into the performance of each model and select the EfficientNet model with the best performance for the generation of subsequent security posture evaluation data.Ultimately, the developed security grade protection assessment system provides a reliable and efficient evaluation means for the network security.