Research And Application Of Network Security Situation Assessment Based On Data Fusion

With the increasing scale and complexity of the network,network attacks emerge in endlessly.The traditional network security defense measure is a single security device defense.Obviously,it has been unable to deal with more and more serious network security problems,so we should turn to a global defense system which integrates a large number of security device log information.In this context,network security situation assessment technology emerges as the times require.Network security situation assessment technology can collect a large number of security data from all kinds of security devices,evaluate the security situation of the network through data fusion and other technologies,fully and accurately reflect the security situation and change trend of the whole network.Among them,data fusion is the core of network security situation assessment.Therefore,the research on network security situation assessment and data fusion is very important and practical.Based on the analysis of data fusion technology and network security situation assessment,aiming at solving the problems caused by the defense of single security device,such as difficult to accurately reflect the network security situation,etc.,this thesis puts forward a hierarchical network security situation assessment model based on multisource heterogeneous data,and designs and implements the network security situation assessment system,so as to make the network security administrators can intuitively understand the security situation and change trend of the network.The work completed in this thesis mainly includes the following four aspects:(1)A hierarchical network security situation assessment model based on multi-source data fusion is established,which is divided into situation factor extraction layer,node situation analysis layer and network situation analysis layer from bottom to top.By fusing the situation indicators extracted from the situation element layer,the security situation assessment of nodes is realized.Then,the weight of the nodes and the security situation of the nodes are integrated to realize the security situation evaluation of the whole network.(2)The improved D-S evidence theory algorithm is used to evaluate the security situation of nodes.In order to solve the problem that BPA is too subjective,the BP neural network optimized by adaptive genetic algorithm is introduced to make the evaluation result more accurate.The improved analytic hierarchy process(AHP)and entropy method are used to evaluate the weight of nodes,which solves the problem of too subjective or too objective in the process of weight determination.(3)The hierarchical network security situation assessment model based on multisource heterogeneous data proposed in this thesis is verified by experiments.The data of all kinds of security devices deployed in the information center is used,and then the experimental results are analyzed.The experimental results prove the validity of the model,which can objectively and comprehensively evaluate the real security situation of the network.(4)Based on the research of evaluation model and algorithm,a network security situation evaluation system is designed and implemented,which enables users to intuitively understand the network security situation and security trend,so as to take measures in time.