一种面向多次发布的隐私保护模型  

A privacy protection model for data re-publication

作　　者：赵皎[1] 沈明玉[1] 胡学钢[1] 王正彬[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2017年第10期1338-1342,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61273292)

摘　　要：文章提出了一种面向多次发布的数据库隐私保护模型,通过等价类的动态调整来隐藏数据和等价类间的映射关系,降低隐私泄露的风险。利用伪数据调节数据的多样性以满足匿名规则的要求,伪数据亦可作为噪声数据增加攻击者的分析难度,提高隐私保护强度。在UCI数据库上进行的仿真实验结果表明,该模型能够有效减少因多次发布带来的隐私泄露。A privacy protection model for data re-publication is put forward. The mapping relations be- tween data and equivalent classes are hidden by adjusting equivalence classes dynamically, which can reduce the risk of privacy leakage. Pseudo data is used to adjust data diversity to meet the diversity re- quirement of anonymous rules, and to increase the difficulty of analysis for attackers as noise data. The results of the experiments on the UCI database show that under the premise of improving the di- versity of the released data, this model can effectively reduce the privacy disclosure risks caused by the multiple releases.

关 键 词：隐私保护 匿名规则 多次发布 隐私泄露 限制发布 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]