数据发布中的个性化隐私匿名技术研究  

Research on Anonymity Technique for Personalization Privacy-preserving Data Publishing

作　　者：王波[1,2] 杨静[1] 

机构地区：[1]哈尔滨工程大学计算机科学与技术学院,哈尔滨150001 [2]哈尔滨理工大学自动化学院,哈尔滨150080

出　　处：《计算机科学》2012年第4期168-171,200,共5页Computer Science

基　　金：国家自然科学基金(61073041;61073043);黑龙江省自然科学基金(F200901);哈尔滨市学科带头人专项基金(2011RFXXG015)资助

摘　　要：个性化隐私保护是目前数据发布中隐私泄露控制技术研究的热点问题之一。对这方面的研究现状进行综述。首先,在分析不同类型个性化服务需求的基础上,建立相应的个性化隐私匿名模型;其次,根据采用技术的不同,对已有的个性化隐私保护匿名技术进行总结,并对各类技术的基本原理、特性进行概括性的阐述。同时,根据算法所采用信息度量的差异,给出现有个性化隐私度量的方法与标准。最后,在对比分析已有研究的基础上,总结全文并展望了个性化隐私保护匿名技术的进一步研究方向。Privacy-preserving data publishing for personalization is a hot research topic in technique for controlling privacy disclosure in data publishing in recent years.An overview of this area was given in this survey.First,on the basis of analyzing types of different personalization service,relevant anonymization models of personalization privacy were built.Second,according to the different adopting techniques,a summarization of the art of personalization privacy-preserving techniques was given,and the fundamental principles and characteristics of various techniques were generally described.In addition,some existing privacy measure methods and standards were provided,according to the differences of information measure of adopted algorithms.Finally,based on the comparison and analysis of existing researches,future research directions of privacy-preserving data publishing for personalization were forecasted.

关 键 词：数据发布 个性化 隐私保护 匿名化 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]