A network security situation assessment method based on sae+bpnn

Abstract

The invention discloses a network security situation assessment method based on SAE+BPNN, comprising: extracting network security situation awareness index data to be evaluated; performing normalization processing on the extracted index data; normalizing the index data after normalization processing Input the trained deep autoencoder neural network to reduce the dimensionality of the normalized indicator data; input the dimensionally reduced indicator data into the trained BP neural network to evaluate the network security situation. Aiming at the problems that the required model complexity is high, the model calculation time is long, and the accuracy rate cannot be improved when the BP neural network processes sparse high-dimensional data, the deep self-encoding neural network is used to reduce the dimensionality of the data to ensure that the data The nonlinear relationship with the label can optimize the model, reduce the complexity of the model, reduce the training time of the model, and improve the robustness and generalization of the model.

Description

technical field [0001] The invention relates to the technical field of network security, in particular to a network security situation assessment method based on SAE+BPNN. Background technique [0002] With the popularization of the Internet and the development of network technology, the scale of the network is increasing, and the problem of network security is becoming more and more prominent. The assessment of the network security situation has also become an increasingly urgent need. As an important part of network security situation awareness, network security situation assessment mainly uses assessment methods to comprehensively analyze various security factors of the network, obtain corresponding security situation values, and provide users with accurate security status evaluation and network security trend estimation. At present, the common network security situation assessment methods mainly include neural network, Bayesian reasoning, support vector machine, D-S evi...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the purpose of the present invention is to provide a network security situation assessment method based on SAE+BPNN, using deep auto-encoder neural network (StackedAuto-Encoder, SAE) plus BP neural network (error BackPropagation Neural Network, BPNN), to solve complex In the network environment, the data dimension of network security indicators is too large, the training calculation is large, the training is slow, and the parameters are various, which affects the evaluation efficiency.

Images