This study aims to use neural network theory to analyze and evaluate computer network security. Firstly, the evaluation model of computer network security was given based on relevant literature, and the corresponding index system was constructed, including 19 indicators of management security, physical security, and logical security. Then, the index normalization standard was proposed and the index security level was set. Finally, computer network security was evaluated according to the neural network. Results show that security management strategy has the greatest impact on computer network security, followed by routing control and data encryption.
HuaxinZ., Power grid security assessment combining AHP with neuralnetwork, Modern Electronics Technique21 (2016), 168–171.
2.
YanS., Evaluation of network security situation based on grey relational analysis and support vector machine, Laser Journal4 (2015), 147–150.
3.
FangleiL., ShaochengY. and JiangZ., Improved network security situational assessment method based on FAHP, Journal of Computer Applications9 (2014), 2622–2626.
4.
SitingW. and BiaoW., Computer network security evaluation simulation model based on neural network, Modern Electronics Technique3 (2017), 89–91.
5.
RenjieW., Application research of computer network securityevaluation based on network security, Computer Simulation11 (2011), 126–128.
6.
HuaxiC., YuoqiangG. and BaofengY., Network security assessment model of coupling empowerment, Computer Engineering22 (2011), 99–101.
7.
ZhifengH., Research on security grade classification of computer network based on discrete Hopfield network, Modern Electronics Technique21 (2015), 92–95.
8.
JunZ., Evaluation of computer network security based on adaptive BP neural network, Modern Electronics Technique23 (2015), 85–88.
9.
YeS., Study on computer network security evaluation based onsupport vector regression machine, Modern Electronics Technique7 (2016), 89–92.
10.
LixiaX., YachaoW. and JinboY., Network security situation awareness based on neural networks, Journal of Tsinghua University (Science and Technology)12 (2013), 1750–1760.
11.
LinoA., RochaÁ. and SizoA., Virtual teaching and learningenvironments: Automatic evaluation with artificial neural networks, luster Computing (2017), 1–11.
