Design Of Network Security Situational Awareness Platform Based On Network Data

With the deepening of information construction and the emergence and development of information technology such as big data,Internet of things,cloud computing and mobile internet,all walks of life are facing a more complex situation in the field of IT network security than before.New information security problems are constantly emerging.The importance of network security situational awareness is becoming more and more important.More and more attention has been paid to it by all walks of life.Network security situational awareness is a kind of multi-source heterogeneous data fusion of traditional detection.It uses information fusion method to grasp the overall security situation of the network from a macro perspective,and to warn and communicate the threatened network nodes,so as to realize the active defense of network security,which can assist network administrators in real-time monitoring.Network security status provides assistant decision-making for network protection strategy.On the basis of previous research on network security situational awareness,this paper proposes a framework of network security situational awareness based on Multi-heterogeneous data fusion,which adopts a bottom-up,part-to-whole quantitative evaluation method: introducing Bayesian network to fuse the information of the underlying multi-source heterogeneous security situational data to form vulnerability.According to the importance of different nodes in the network and the importance of each security factor,the multi-module fusion method is used to fuse the security situation of the nodes and form the security situation index of the whole network system.On this basis,the long-short memory neural network is adopted.Network security situation prediction: In view of the uneven scaling of network situation index series,the method of standardization of mean square deviation is introduced to pre-process the original data,and then the processed data is input into :Long short-term memory network for training.Finally,the predicted results are standardized and inversely processed to obtain the network situation prediction results.According to the research framework of this paper,the network security situational awareness platform is designed.In the experimental environment,the performance of the actual network security situational awareness platform is tested by using the relevant data.The experimental results show that the proposed network situational assessment and prediction method can perceive the network security situation and verify the method.