An intelligent adaptive sensitive data recognition system and method

Abstract

The self-adaptive sensitive data identification mode provided by the invention solves the problems existing in the sensitive data identification under the big data environment. The invention solves the problem of heavy workload and low efficiency of manually defining sensitive data and metadata, and effectively improves the working efficiency of sensitive data identification; The invention improves the accuracy of the identification of the sensitive data by mining the semantic features of the sensitive data. The invention combines three kinds of sensitive data recognition modes based on text content, metadata and knowledge base, optimizes the flow of sensitive data recognition, and improves the accuracy and efficiency of sensitive data recognition. The invention proposes the self-adaptivemanagement of the sensitive type, solves the problem that the new sensitive type is difficult to be added, and improves the flexible adaptation degree of the sensitive type to the actual demand.

Description

technical field [0001] The invention relates to the cross-technical field of computer technology and information security, in particular to an intelligent sensitive data identification system and method based on big data. Background technique [0002] In the era of big data, the data is huge in scale, growing rapidly, with various types and structures, and the description is not standardized, and these data contain a large amount of sensitive data, and 85% of them are unstructured data, which affects the efficiency of sensitive data identification. and accuracy pose enormous challenges. [0003] Traditional sensitive data discovery methods mainly adopt two methods based on manual definition and regular expression. [0004] 1. The method based on manual definition is to define keywords or metadata information, and then match keywords and metadata information to discover sensitive data in the business system; [0005] 2. The method based on regular expressions is to study th...

AI Technical Summary

Problems solved by technology

[0007] 1. The work of manually defining sensitive keywords and metadata is becoming more and more arduous and inefficient;

[0008] 2. Some sensitive data have structural characteristics, such as ID number, bank card number and other sensitive types, which can be matched by regular expressions, but for sensitive data without structural characteristics, such as sensitive types such as addresses and names, regular expressions cannot be used Conduct sensitive data discovery;

[0009] 3. The regular expression method needs to study the characteristics of each type of sensitive data to discover sensitive data. With the increase of sensitive types, there will be more and more regular expressions, which directly affects the efficiency of sensitive data discovery, and it is difficult to maintain the rule base. a waste of resource;

[0010] 4. Based on regular expressions and manual definition of sensitive keywords and metadata, only sensitive data that conforms to the rules and matches successfully can be identified. Sensitive data with sensitive semantics will be missed, which reduces the accuracy of sensitive data identification and cannot prevent the leakage of sensitive data ;

[0011] 5. When sensitive requirements change, it takes a lot of time and effort to modify the new sensitive type

Images