Method for processing big data based on l-diversity rules and MDAV algorithm

Abstract

The invention belongs to the technical field of privacy protection of a database and discloses a method for processing big data based on l-diversity rules and an MDAV algorithm. According to the method, the MDAV algorithm is improved, a new algorithm, namely an ''(l,d,e)-MDAV algorithm'' is generated, and compared with MDAV, the new algorithm can resist homogeneity attacks and effectively reduce information leakage risks while guaranteeing high efficiency and low information loss. It is proved through experiments that the new algorithm has a good effect on processing anonymization of data tables. According to the method, a manually-given difference value with a center of mass has personalized further research value. A user can set an e value according to the demand for self-confidentiality, and maximum privacy protection and a minimum leakage risk can be realized.

Description

technical field [0001] The invention belongs to the technical field of privacy security in data release, and proposes a method for processing big data based on the l-diversity rule and the MDAV algorithm based on the l-diversity rule and the MDAV algorithm. Background technique [0002] The issue of privacy protection in data publishing was first raised in the field of statistical leakage control, and then gradually penetrated into the entire information technology field. In the field of statistical leak control, methods such as micro-aggregation, randomization, sampling, and adding white noise are mainly used to protect information. While trying to ensure the statistics and availability of processed data and the security of private information, more information is retained. Useful information, balance the relationship between data confidentiality and availability. After years of development, the privacy protection technology released in the data mainly focuses on two aspec...

AI Technical Summary

Problems solved by technology

[0008] The existing l-diversity rule effectively avoids the problem that k-anonymity cannot resist gay attacks, but it still has the problems of high time complexity of k-anonymity algorithm, long calculation time, and large amount of information loss

[0009] The MDAV algorithm is a classic fixed-length micro-aggregation algorithm. It has the advantages of high algorithm efficiency and small information loss. However, the MDAV algorithm will be attacked by comrades due to the high similarity of tuples in the class after the data set is clustered, thus leaking privacy information

Images