摘要
针对多敏感属性数据中l-多样性问题及现有隐私保护方法可能导致过高隐匿率的问题,提出一种基于属性分类的多敏感属性隐私保护方法。根据各自敏感属性值的多样性及隐私重要性对属性进行分类,分别设置不同的多样性参数l并进行分组,使之满足各自的多样性要求。实验结果表明,该方法可以有效地保护隐私数据,同时减少数据的隐匿率,提高共享数据的可用性。
In view of the l-diversity problem in data with multiple sensitive attributes and the high hide ratio that presents privacy preserving methods may cause,a sensitive Attributes Classification Based Grouping(ACBG) privacy preserving method is proposed.It classifies the sensitive attributes according to the diversity and importance of each sensitive attribute,and sets different diverse values for them and groups the data,so it can meet the l-diversity for each.Experimental results show that this approach can protect privacy of data and reduce the hide ratio and enforce the usability of the shared data.
出处
《计算机工程》
CAS
CSCD
2013年第8期177-180,186,共5页
Computer Engineering
关键词
隐私保护
属性分类
多敏感属性
l-多样性
有损连接
数据共享
privacy preserving
attributes classification
multiple sensitive attributes
l-diversity
lossy join
data sharing
作者简介
王茜(1964--),女,教授,主研方向:信息安全,电子商务;
李艳军,硕士研究生E—mail:51yanjun@163.com
刘泓,硕士研究生