分布式环境下保持隐私的聚类挖掘算法  

Privacy preserving clustering over distributed data

作　　者：张国荣[1] 印鉴[2] 

机构地区：[1]广州美术学院计算机基础教研室,广州510260 [2]中山大学信息科学与技术学院,广州510275

出　　处：《计算机工程与应用》2007年第18期165-167,180,共4页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.60573097);广东省自然科学基金(the Natural Science Foundation of Guangdong Province of China under Grant No.05200302;No.06104916);国家科技计划项目 (the Key Technologies R&D Program of China under Grant No.2004BA721A02);广东省科技计划项目(the Key Technologies R&D Program of Guangdong(Province);China under Grant No.2005B10101032);高等学校博士学科点专项科研基金(the China Specialized Research Fund for the Doctoral Program of Higher Education under Grant No.20050558017)。

摘　　要：隐私保护是数据挖掘中一个重要的研究方向。针对如何在不共享精确数据的条件下,应用k-平均聚类算法从数据中发现有意义知识的问题,提出了一种基于安全多方计算的算法。算法利用半可信第三方参与下的安全求平均值协议,实现了在分布式数据中进行k-平均聚类挖掘时隐私保护的要求。实验表明算法能很好的隐藏数据,保护隐私信息,且对聚类的结果没有影响。Privacy preserving is an important direction for data mining research. This paper is concentrated on the issue of using k-means clustering algorithm to mining interesting accurate models without sharing precise individual data records,and proposes a method based on secure multi-party computation model. The method uses a secure_mean protocol to accomplish privacy-preserv ing k-means clustering that based on a semi-trusted third-party server. It efficiently hides attribute values,preserves privacy in formation and guarantees valid clustering results.

关 键 词：数据挖掘 隐私保护 k-平均聚类 安全多方计算 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]