保护社区结构的社会网络匿名技术  

Social network anonymity technology for protecting community structure

作　　者：李娜[1] 张晓琳[1] 王永平[1] 高鹭[1] 刘立新[1,2] LI Na;ZHANG Xiao-lin;WANG Yong-ping;GAO Lu;LIU Li-xin(School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China;School of Information,Renmin University of China,Beijing 100872,China)

机构地区：[1]内蒙古科技大学信息工程学院,内蒙古包头014010 [2]中国人民大学信息学院,北京100872

出　　处：《计算机工程与设计》2022年第7期1816-1824,共9页Computer Engineering and Design

基　　金：国家自然科学基金项目(61562065);内蒙古自然科学基金项目(2019MS06001)。

摘　　要：针对当前社会网络隐私保护方法存在社区结构破坏严重、单工作站处理数据能力低等不足,提出一种保护社区结构的社会网络度匿名SNDA-PCS(social network degree anonymity for protecting community structure)方法。社会网络社区发现使用分裂聚集算法,由聚合向量构造的压缩二叉树分组匿名度序列,添加虚拟顶点构造匿名图,根据顶点所属社区设计虚拟顶点删除-添加算法以提高发布图数据可用性。SNDA-PCS算法基于大规模并行图处理系统GraphX实现,实验结果表明,SNDA-PCS算法在满足匿名要求的同时保证了社区结构的可用性。The current social network privacy protection methods have some shortcomings,such as serious destruction of community structure and poor data processing ability of single workstation.A social network degree anonymity method was proposed to protect community structure(SNDA-PCS).Divide and agglomerate algorithm was used for social network community detection.The grouping and anonymous results based on compressed binary tree constructed by aggregate vector were obtained.The purpose of adding virtual vertices to the original graph was to obtain anonymous social network.To improve the data availability of published graph,a virtual vertex removal-addition algorithm was designed according to the community to which the vertex belongs.The realization of SNDA-PCS algorithm was based on GraphX,a large-scale parallel graph processing system.Experimental results show that the proposed algorithm can ensure the availability of community structure well while meeting the requirement of anonymity.

关 键 词：社会网络匿名 压缩二叉树 GraphX 社区结构 可用性 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]