基于聚类结构编码的差分隐私异构数据发布  

A DIFFERENTIAL PRIVACY PUBLISHING SCHEME OF HETEROGENEOUS DATA BASED ON CLUSTERING STRUCTURE CODING

作　　者：高海燕[1] 高晋阳 郑志华 Gao Haiyan;Gao Jinyang;Zheng Zhihua(Electronic Information College,Jinzhong Vocational and Technical College,Jinzhong 030600,Shanxi,China;School of Instruments and Electronics,Zhongbei University,Taiyuan 030051,Shanxi,China)

机构地区：[1]晋中职业技术学院电子信息学院,山西晋中030600 [2]中北大学仪器与电子学院,山西太原030051

出　　处：《计算机应用与软件》2023年第7期18-25,60,共9页Computer Applications and Software

基　　金：国家自然科学基金项目(51475368);2018年山西省高等学校大学生创新创业训练计划项目(2018328)。

摘　　要：针对异构数据发布的隐私保护以及数据挖掘泛化性问题,提出一种用于聚类分析的异构数据差分隐私发布方案。为了解决处理隐私信息后缺乏正确引导的问题,将原始数据分组为集群,并利用集群标签对数据的集群结构进行编码,还为异构数据定制了一个同时考虑关系属性和集值属性的距离度量集群。在保留集群结构的同时迭代地概括原始数据。进一步在原始数据中加入噪声从而满足ε-差分隐私的要求。在满足差分隐私原则的前提下,提出一种同时处理关系数据和集值数据的不确定性算法,不同类型的数据以类似的方式进行匿名化。通过实验验证了该方法能够有效解决异构数据发布问题。Aimed at the privacy protection of heterogeneous data publishing and the generalization of data mining,a differential privacy publishing scheme of heterogeneous data for clustering analysis is proposed.In order to solve the problem of lack of correct guidance after dealing with privacy information,the original data was grouped into clusters,and the cluster structure of data was coded by using the cluster label.A distance measurement cluster considering both relationship attribute and set-valued attribute was customized for heterogeneous data.The original data was summarized iteratively while retaining the cluster structure.Furthermore,noise was added to the original data to meet the requirement ofε-differential privacy.On the premise of satisfying the principle of differential privacy,an uncertainty algorithm was proposed to process relational data and set-valued data simultaneously.Different types of data were anonymized in a similar way.Experiments show that this method can effectively solve the problem of heterogeneous data publishing.

关 键 词：数据发布 异构数据 差分隐私 聚类分析 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP3[自动化与计算机技术—控制科学与工程]