Modeling and Analysis of Network Security Situation Prediction Based on Covariance Likelihood Neural

Security situation is the premise of network security warning. For lack of self-learning on situation data processing in existing complex network, a modeling and analysis of network security situation prediction based on covariance likelihood neural is presented. With the introduction of the error covariance likelihood function, and considering the impact of sample noise, the network security situation prediction model using the situation sequences as input sequences, and in the back-propagation to achieve the parameters adjustment. Results show that the model can take advantage of the relationship characteristics between the complexity and efficiency in complex neural networks, and the method has good performance of situation prediction.