Research Of Personal Privacy Anonymous Method

In the rapid developmentof information technology today, all kinds of work collect alarge amount of data in the process of using information management system. A number ofthese datas relate to personal or corporate privacy so that loss of privacy become inevitablesecurity risk in the process of collection and release of these data, so the privacy preservationtechnology of data has been put on agenda by academia and industry.Personalized privacy anonymous that has been widespread concerned by academia is oneof the important research of privacy preservation technology, andmany scholars dedicated torelated research, and made a lot of meaningful results. However, no enough research has beendone for personalization of privacy preservation, and as for that existing personalized privacyanonymous technology can not meet the need for both individual need-orientedpersonalization and sensitive property-oriented personalization, this paper introduce granularcomputing thinking, the innovative work is the following:Firstly,granulating(α, k)–anonymous model that introduce the idea of granularcomputingis proposed, first establishing collection of decision-making degree for privacypreservation based on rough set theory to depict different individualrequirementsof differentprotection to the same sensitive value of sensitive properties; sencondly,establishing top-levelgranularity spacebase on different valuesof decision-making degree collection; finally, givingdifferent frequency constraints for sensitive values in each top-level granularity space, tomeet the personalized anonymous request of sensitive-oriented value.Secondly, granulating(α, k)–anonymous algorithm is proposed. The granulating(α, k)–anonymous algorithm is the specific realization about granulating(α, k)–anonymous model.Other than other algorithms, this algorithm has the property of personalized privacypreservation that is individual need-oriented as well as sensitive property value-oriented, andobtain more comprehensive and more reasonable personal privacy implementation of smallerloss of information and executing time. In this sense, the granulating (α, k)–anonymousalgorithm proposed in this paper has more advantage than other existing personalized privacypreservation algorithms.Finally, making a lot of experiment to verify the rationality and effectiveness ofgranulating(α, k)–anonymous model and algorithm proposed. Experimental results showgranulating(α, k)–anonymous model proposed is reasonable, granulating(α, k)–anonymousalgorithm is correct, and under the premise of the effectiveness of privacy preservation, themodel proposed in the paper embody better personalization of privacy preservation than existing model.