介绍了k-匿名的基本概念及相关研究,分析了k-匿名应用的局限性及k-匿名表存在的缺点。基于这种现状,提出了对k-匿名一种新的改进方法。该方法基于个人化匿名的观点,个人可以通过分类树中的节点指定自己的隐私保护程度。该方法将概括分为两步QI-概括和SA-概括,从而,实现了满足每个人隐私要求的最小量的概括,最大程度地保留了原始数据中信息。
In this paper, the basic concept and relevant research of the k-anonymity is presented. The limitation of the k-anonymity and the shortcomings in the k-anonymity tables are analyzed. Ground on this point, a new method that improves k-anonymity is proposed. This method is based on the view of personalized anonymity, i. e., a person can specify the degree of privacy protection for her/his sensitive values through a node in the taxonomy. The generalization is performed in two steps, the first is the QI-generalization, and the second is SA-generalization, and thus, this technique performs the minimum generalizations for satisfying everybody's requirements, and retains the largest amount of information from the microdata.