Research On Network Security Situation Assessment Method Based On CS-BPNN

In recent years,a variety of network security incidents emerge in an endless stream,network security has become a hot topic of society concern,how to perceive,defensive network threats become the focus of network security research.Network security situation assessment(NSSA)as a comprehensive assessment of network security technology,is the focus of the current network security research.Neural network,as an important part of artificial intelligence,plays an important role in NSSA,among them,back propagation(BP)neural network is the most widely used.However,the BP neural network assessment model has a slow convergence rate,lack of local and global search ability.A method of NSSA based on cuckoo search(CS)optimize back propagation neural network(CS-BPNN)is proposed,and the method is verified experimentally.Firstly,it introduces the knowledge of network security situation in theory,analyzes the definition,purpose,function and commonly used methods of NSSA,and compares the advantages and disadvantages of each method.Thus providing the theoretical basis.Secondly,CS-BPNN method is proposed.The assessment model is abstracted as input part,mapping part and output part.The weights and thresholds of the mapping part are coded into cuckoo,and the optimal weights and thresholds are searched by the CS algorithm and the error is adjusted by BP algorithm.Finally,the proposed method of NSSA based on CS-BPNN is experimentally verified.The experimental network is used to simulate the attacks attack on the network,and the situation data are obtained from the network.Compared with the method based on BP neural network and particle swarm optimization optimize BP neural network.The experimental results show that the proposed method has a faster assessment speed and high accuracy.