Data security risk identification method and device based on complex network analysis

Abstract

The embodiment of the invention provides a data security risk identification method and device based on complex network analysis, and the method comprises the steps of collecting related data of a to-be-detected service, and constructing a complex network according to vertex data and boundary data; grouping vertexes in a complex network, obtaining a preset measurement index, and calculating a first risk score of the vertex in each group through the measurement index; obtaining a special structure in the complex network through a preset isomer detection algorithm, and comparing the special structure with the complex network to obtain a second risk score of each vertex; obtaining a black list, a white list and a preset risk propagation algorithm, and calculating a third risk score of each vertex in the complex network; and performing comprehensive calculation according to the first, second and third risk scores of each vertex to obtain a comprehensive risk score of each vertex in the complex network. By adopting the method, the three comprehensive scores can be used as the final risk score of the data, so that the final risk score is comprehensive and higher in accuracy.

Description

technical field [0001] The invention relates to the technical field of data security, in particular to a data security risk identification method and device based on complex network analysis. Background technique [0002] With the development of information technology in the times, data assets have become one of the most important assets of various enterprises. However, in recent years, many enterprises have suffered heavy losses due to data leakage, so data security is becoming more and more important. To protect data security, it is necessary to conduct risk assessments on entities such as accounts, clients, and servers related to data assets. [0003] However, most of the current risk assessments for enterprise data are based on single-side data for model construction, and then data risk prediction through the model. The prediction results obtained by this prediction method are generally not comprehensive enough, and the accuracy is not high enough. Contents of the inve...

AI Technical Summary

Problems solved by technology

[0003] However, most of the current risk assessments for enterprise data are based on single-sided data for model architecture, and then data risk prediction through the model. The prediction results obtained by this prediction method are generally not comprehensive enough, and the accuracy is not high enough.

Images