摘要
隐私保护数据挖掘是在不精确访问原始数据的基础上,挖掘出准确的规则和知识。针对分布式环境下聚类挖掘算法的隐私保护问题,提出了一种基于完全同态加密的分布式聚类挖掘算法(FHE-DK-MEANS算法)。理论分析和实验结果表明,FHE-DK-MEANS算法不仅具有很好的数据隐私性,而且保持了聚类精度。
Privacy preserving data mining is to discover accurate rules and knowledge without precise access to the raw data. This paper focused on privacy preserving clustering algorithms mining in a distributed environment, and presented a fully homomorphic encryption algorithm based on distributed k-means (FHE-DK-MEANS algorithm). Theoretical analysis and experimental results show that FHE-DK-MEANS algorithm can provide better privacy and accuracy.
出处
《计算机科学》
CSCD
北大核心
2012年第3期160-162,共3页
Computer Science
基金
国家自然科学基金项目(60875029)
北京市科技计划专项课题资助
关键词
数据挖掘
隐私保护
聚类
分布式数据
Data mining, Privacy preserving, Clustering, Distributed data