电子学报

• 学术论文 • 上一篇    下一篇

面向敏感性攻击的多敏感属性数据逆聚类隐私保护方法

张冰, 杨静, 张健沛, 谢静   

  1. 哈尔滨工程大学计算机科学与技术学院, 黑龙江哈尔滨 150001
  • 收稿日期:2013-05-07 修回日期:2013-09-02 出版日期:2014-05-25
    • 作者简介:
    • 张 冰 女,1986年生于黑龙江哈尔滨.哈尔滨工程大学计算机科学与技术学院博士研究生.主要研究方向为数据挖掘、隐私保护. E-mail:zhangbing006@hrbeu.edu.cn杨 静 女,1962年生于黑龙江哈尔滨.哈尔滨工程大学计算机科学与技术学院教授、博士生导师.主要研究方向为数据库与知识工程、数据挖掘、隐私保护、软件理论等. E-mail:yangjing@hrbeu.edu.cn
    • 基金资助:
    • [JP2]国家自然科学基金 (No.61370083,No.61073043,No.61073041); 高等学校博士学科点专项科研基金 (No.20112304110011,No.20121204110012); 哈尔滨市科技创新人才研究专项资金 (优秀学科带头人) (No.2011RFXXG015)

A Multi Sensitive Attribute Data Inverse Clustering Privacy Preserving Algorithm for Sensitivity Attack

ZHANG Bing, YANG Jing, ZHANG Jian-pei, XIE Jing   

  1. College of Computer Science and Technology, Harbin Engineering University, Harbin, Heilongjiang 150001, China
  • Received:2013-05-07 Revised:2013-09-02 Online:2014-05-25 Published:2014-05-25
    • Supported by:
    • National Natural Science Foundation of China (No.61370083, No.61073043, No.61073041); Research Fund for the Doctoral Program of Higher Education of China (No.20112304110011, No.20121204110012); Harbin Science and Technology Innovation Talents Research Fund of Heilongjiang Province  (Excellent Academic Leader) (No.2011RFXXG015)

摘要: 针对传统l-多样性模型仅考虑等价类中敏感值形式上的差异,而忽略敏感值的敏感度差异,且难以抵御一种新的攻击方式——敏感性攻击的问题,提出了一种使用逆文档频率IDF度量敏感值的敏感度的方法,并使用属性分解的方式构造敏感组,以避免多敏感属性数据表的QI属性泛化造成的高信息损失.同时,还提出了一种面向敏感性攻击的多敏感属性(l1,l2,…,l<em>d)-多样性隐私保护算法MICD,该算法通过敏感度的逆聚类实现敏感组中敏感值的敏感度差异,以提高多敏感属性数据表抵御敏感性攻击的能力.实验结果表明,MICD算法能够较好的抵御敏感性攻击,且具有较小的信息损失量.

关键词: 隐私保护, 敏感性攻击, 逆聚类, 多敏感属性, (l1,l2,…,ld)-多样性, 敏感度差异

Abstract: In allusion to l-diversity model not considering sensitivity differences between the sensitive attributes,a new attack pattern which named sensitivity attack was proposed.Secondly,a new sensitive groups constructing method which based on sensitive attributes decomposition was proposed,and a keyword weight evaluation method called IDF was used to measure the sensitivity of the sensitive values.At the same time,a multi sensitive attributes (l1,l2,…,ld)-diversity privacy preserving method for sensitivity attack which called MICD was proposed,which guaranteed the sensitivity difference between sensitive values in sensitive groups by sensitivity inverse clustering.Experiment results demonstrated that the MICD algorithm could better protect sensitive attributes against sensitivity attack,and more effective on information loss.

Key words: privacy preserving, sensitivity attack, inverse clustering, multi sensitive attribute, (l1,l2,…,ld)-diversity, sensitivity degree difference

中图分类号: