Hierarchical homomorphic encryption based privacy preserving distributed association rule mining

Abstract

Privacy is an important issue in the field of distributed association rule mining, where multiple parties collaborate to perform mining on the collective data. The parties do not want to reveal sensitive data to other parties. Most of the existing techniques for privacy preserving distributed association rule mining suffer from weak privacy guarantees and have a high computational cost involved. We propose a novel privacy preserving distributed association rule mining scheme based on Paillier additive homomorphic cryptosystem. The experimental results demonstrate that the proposed scheme is more efficient and scalable compared to the existing techniques based on homomorphic encryption. � 2014 IEEE.