数据库中的知识隐藏  

Knowledge Hiding in Database

作　　者：郭宇红[1] 童云海[2] 唐世渭[1] 杨冬青[1] 

机构地区：[1]北京大学 计算机科学技术系,北京100871 [2]北京大学 视觉与听觉信息处理国家重点实验室,北京100871

出　　处：《软件学报》2007年第11期2782-2799,共18页Journal of Software

基　　金：No.60403041(国家自然科学基金)~~

摘　　要：伴随着数据共享、隐私保护、知识发现等多重需求而产生的PPDM(privacy preserving data mining),成为数据挖掘和信息安全领域近几年来的研究热点.PPDM中主要考虑两个层面的问题:一是敏感数据的隐藏与保护;二是数据中蕴涵的敏感知识的隐藏与保护(knowledge hiding in database,简称KHD).对目前的KHD技术进行分类和综述.首先介绍KHD产生的背景,然后着重讨论敏感关联规则隐藏技术和分类规则隐藏技术,接着探讨KHD方法的评估指标,最后归结出KHD后续研究的3个方向:数据修改技巧中基于目标距离的优化测度函数设计、数据重构技巧中的反向频繁项集挖掘以及基于数据抽样技巧的通用知识隐藏方法设计.Motivated by the multiple requirements of data sharing, privacy preserving, privacy preserving data mining （PPDM） has become the research hotspot in data mining and information security fields. Two main problem are addressed in PPDM： One is the protection of sensitive raw data; the other is the protection of sensitive knowledge contained in the data, which is also called knowledge hiding in database （KHD）. This paper gives a survey on the current KHD techniques. It first introduces the background in which KHD appears. Then it mainly presents the techniques on sensitive association rule hiding and classification rule hiding. Evaluation of KHD methods is discussed after that. Finally, it points out three future research directions of KHD： Design of measure function based on target distance in data modification techniques, inverse frequent set mining in data reconstruction techniques and design of general KHD method based on data sampling.

关 键 词：知识隐藏 KHD(knowledge hiding in database) 敏感规则 隐私保护 反向挖掘 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]