Privacy Preserving Mining of Global Association Rules on Distributed Dataset

Abstract

The issue of maintaining privacy in data mining has attracted considerable attention over the last few years. In this paper, we continue the investigation of the techniques of distorting data in developing data mining techniques without compromising customer privacy and present a privacy preserving data mining algorithm for finding frequent itemsets and mining association rules on distributed data allocated at different sites. Experimental results show that such a distortion approach can provide high privacy of individual information and at the same time acquire a high level of accuracy in the mining result.