分布式环境下保持隐私的关联规则挖掘算法  

Privacy Preserving Distributed Mining Algorithm of Association Rules

作　　者：王恩彬[1] 吴陈[1] 曾庆军[1] 

机构地区：[1]江苏科技大学计算机学院,镇江212003

出　　处：《科学技术与工程》2009年第1期135-138,151,共5页Science Technology and Engineering

基　　金：江苏省科技计划项目(BE2006086)资助

摘　　要：隐私保护是当前数据挖掘领域中一个十分重要的研究方向,其目的是要在不精确访问真实原始数据的条件下,得到准确的模型和分析结果。为了提高对隐私数据的保护程度和挖掘结果的准确性,研究了一种基于向量点积的分布式关联规则挖掘算法。此算法在分布式环境下,利用保持隐私数据挖掘的基本方法和安全两方计算协议,可以在不泄露任何隐私的基础上有效地对垂直型数据分布进行挖掘。Privacy preservation is one of the most important topics in data mining. The purpose is to discover accurate model and analyzable results without precise access to the original data. In order to improve the privacy preservation and mining accuracy, an algorithm based on dot product of vector for distributed mining association rules is presented. Based on the distributed environment, this algorithm can run effectively on the vertical data distribution without revealing any unnecessary information using the basic means of privacy preserving and the protocol of secure two-party computation.

关 键 词：分布式数据挖掘 关联规则 隐私保持 安全两方计算 

分 类 号：TP309.2[自动化与计算机技术—计算机系统结构]