文档介绍：第 29 卷第 2 期计算机应用研究畅29 畅2
2012 年 2 月 Vol 畅2012No
Application Research puters Feb
基于聚类的数据敏感属性匿名保护算法倡
1 1 2
李珊珊, 朱玉全, 陈耿
(, 江苏镇江 212013; , 南京 211815)
摘要: 为了防止数据敏感属性的泄露,需要对数据敏感属性进行匿名保护。针对 l唱多样性模型当前已提出的
算法大多是建立在概念层次结构的基础上,该方法会导致不必要的信息损失。为此,将基于属性泛化层次距离
算法中的距离度量方法与聚类结合,提出了一种基于聚类的数据敏感属性匿名保护算法。该算法按照 l唱
KACA
多样性模型的要求对数据集进行聚类。实验结果表明,该算法既能对数据中的敏感属性值进行匿名保护,又能
降低信息的损失程度。
关键词: 敏感属性; l唱多样性; 聚类; 信息损失
中图分类号: 391 文献标志码: 文章编号: 1001唱3695(2012)02唱0469唱03
TP A
: /. .
doi j issn
唱
Clustering based algorithm for data sensitive
attributes anonymous protection
唱 1 , 唱 1 , 2
LI Shan shan ZHU Yu quan CHEN Geng
( puter Science munications Engineering, Jiangsu University, Zhenjiang Jiangsu 212013, China; of Infor唱
&
mation Science, Nanjing Audit University, Nanjing 211815, China)
Abstract: ,
In order to prevent the disclosure of data sensitive attributes it requires preserving the anonymity of data sensitive
. l唱, 唱
attributes The current algorithm. that has, proposed to meet diversity is mostly唱 based on the hierarchy which can lead to un唱
necessary information loss For this reason this paper proposed a clustering based algorithm for data sensitive attributes anony
, k唱唱
mous protection it adopted an improved distance measure method which was from achieving anonymity