An efficient method for privacy preserving data mining in secure multiparty computation

Abstract

Secure multiparty computation allows multiple parties to participate in a computation. SMC (secure multiparty computation) assumes n parties where n>1. All the parties jointly compute a function. Privacy preserving data mining has become an emerging field in the secure multiparty computation. Privacy preserving data mining preserves the privacy of individual's data. Privacy preserving data mining outputs have the property that the only information learned by the different parties is only the output of the algorithm. In this paper, we discuss an innovative protocol. This protocol uses both actual and idyllic model. By using both the models, we are providing more security and privacy. We break the data blocks into segments and redistribute the segments among all the parties. The key idea is that, whatever computed by a party participating in the protocol, computation based on its input and output only. This is a scenario where it is impossible to know the private data of some other party.