CRYPPAR: An efficient framework for privacy preserving association rule mining over vertically partitioned data
Duc H. Tran, Wee Keong Ng, Wei Zha · 2009
Building a real system is one of the major challenges of privacy-preserving data mining (PPDM). In this paper, we propose CRYPPAR, a novel, full-fledged framework for privacy preserving association rule mining based on a cryptographic approach. We use secure scalar product protocols and public-key cryptosystems in CRYPPAR to efficiently mine association rules over vertically partitioned data. We also introduce a partial topology to lower communication cost as much as possible. Empirical results show that the framework is efficient in privacy-preserving association rules and may become a general framework for PPDM systems.