Research And Application Of Personal Privacy Protection In Data Publishing

In recent years,with the advent of the information age,the network technology,the data storage technology and the high performance processor technology develop rapidly,the collection,publishing and analysis of massive data have become more and more convenient,the information sharing between the individual and the organization becomes more and more common.But at the same time,data privacy is threatened.Therefore,the research of personal privacy protection technology in data publishing becomes a hot research direction.The technology of anonymity is the main technology used in privacy protection at present.The main work of this paper is to study the privacy protection of multi sensitive attributes in the anonymity technology.The work done in this paper is as follows:Firstly,a personalized(α,l)-anonymous model for multi sensitive attributes is proposed.This paper made deep analysis on the data publishing technology for more sensitive property and personalized anonymity technology and the problems of relative algorithm of their respective areas,aiming at the defects of multi-dimension bucket packet technology and personalized anonymity technology,the personalized(α,l)-anonymity model for multiple sensitive attributes is proposed.This model is based on anonymous multi-dimension bucket according the different sensitivity of sensitive values in the original data to set individual constraints accordingly,construct multi-dimension buckets,then to group,which is to ensure the diversity of sensitive value in each packet of the published data,and to individualized restraint the frequency for different sensitive values.At the same time,multi-sensitive personal-(α,l)disorder grouping algorithm,that is,MSPDG algorithm to realize the model,the experimental results show that the model can solve the problems of insufficient to protect and excessive protection of multiple sensitive attributes sets in data publishing,strengthen privacy protection,reduce the information hiding rate,improve the data availability.Secondly,the maximum selectivity first algorithm,that is,MSF algorithm is proposed.Aiming at the disorder of selecting bucket in grouping process of MSPDG algorithm,this paper puts forward the concept of selectivity.For different needs of the data for the different users set the corresponding selectivity to the bucket.And put forward the maximum selectivity first algorithm.When selecting the non-empty bucket of maximum selectivity,avoids the unstable problem of personal privacy protection technology in data publishing which due to select the bucket disorderly of the MSPDG algorithm in data released and reserves information as much as possible.