The Technology Research Of Network Security Assessment Of Electronic Government Network

With the rapid development of the economic and Internet,E-government came into being in the reform of government information management,at the same time there are some issues about the security of E-government.Network Security Assessment has advantages on vulnerability detection of network system,network situation awareness and intrusion detection.The existing network security assessment technology has a better evaluation result when dealing with the deterministic data,and the situation evaluation of uncertainty information is unsatisfactory.Information system brings difficulties because of complex structure,diversity of physical equipments and large amount of data,low information density.On the one hand,security assessment needs to ensure the accuracy;on the other hand,the security assessment should be real-time.However,the existing security assessment methods either achieve high efficiency at the expense of accuracy or reduce efficiency to achieve high accuracy.Therefore,it is a challenge to meet the accuracy and real-time of the evaluation results.In view of the above challenges,this paper proposes a network security evaluation method based on Grey Relational Analysis and D-S evidence theory.First of all,because of the impact of different evaluation indicators on the network situation is not the same,using of AHP to determine the weight of different evaluation indicators.Secondly,taking into account what membership differences the different indexes bring to the different grades,membership functions of evaluation indices for assessment levels are set and defined an enlarged-weighted membership function to reduce the overall uncertainty.Furthermore,the basic probability assignment of D-S evidence theory is a difficult problem to define,in order to reduce the influence of the subjective factors on the distribution of the basic probability,a method of grey correlation analysis is proposed to solve the basic probability assignment problem.Then,the Mass function is synthesized by D-S evidence theory,and the uncertainty is gradually reduced.The evaluation results are determined according to the confidence function.The experimental results show that the proposed method can reduce the uncertainty of the evaluation results and improve the accuracy and efficiency.Network security situation prediction is one kind of estimate for the future of network security situation which based on the network security assessment,and plays a guiding role in the network security situation.The network security situation is paroxysmal and volatile,so the network security situation prediction method has a good ability to deal with nonlinear problems.In this paper,a network security situation prediction method based on GM(1,1)power model is proposed.GM(1,1)power model has excellent ability to deal with nonlinear problems,the GM(1,1)power model is suitable for small samples and has good practicability.Finally,through the experimental comparison,the network security situation prediction method used in this paper has better prediction accuracy and lower error rate.