Privacy-preserving frequent itemset mining in vertically partitioned database using symmetric homomorphic encryption scheme

Abstract

Frequent itemset mining (FIM) and association rule mining (ARM) are two popular and widely used mining techniques for transactional databases with wide range of applications such as medical diagnosis, market basket analysis, protein sequences, census data, etc. In privacy-preserving frequent itemset mining (PPFIM) over vertically partitioned database, data owners wish to learn frequent itemsets from their concatenated dataset without disclosing their sensitive information. A collusion resistant scheme has been proposed using Du-Atallah's SBDP protocol for multiparty multi-vector scenario which works under two party two-vector case. Also, a scheme is designed by generalising the Du-Atallah's scheme for more than two parties. However it fails in privacy requirements when more than two parties/vectors are considered. In this paper, we give a critique on this approach and focus on efficient and more secure methods for privacy preserving FIM in vertically partitioned databases. To ensure privacy of raw data of different data owners having heterogeneous attributes, we proposed a secure-sum algorithm which uses symmetric homomorphic encryption scheme as a sub-part and a semihonest trusted third party (STTP) environment for calculating the support count of itemsets in privacy preserving manner.