Optimized two party privacy preserving association rule mining using fully homomorphic encryption

  • Authors:
  • Golam Kaosar;Russell Paulet;Xun Yi

  • Affiliations:
  • School of Engineering and Science, Victoria University, Melbourne, VIC, Australia;School of Engineering and Science, Victoria University, Melbourne, VIC, Australia;School of Engineering and Science, Victoria University, Melbourne, VIC, Australia

  • Venue:
  • ICA3PP'11 Proceedings of the 11th international conference on Algorithms and architectures for parallel processing - Volume Part I
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In two party privacy preserving association rule mining, the issue to securely compare two integers is considered as the bottle neck to achieve maximum privacy. Recently proposed fully homomorphic encryption (FHE) scheme by Dijk et.al. can be applied in secure computation. Kaosar, Paulet and Yi have applied it in preserving privacy in two-party association rule mining, but its performance is not very practical due to its huge cyphertext, public key size and complex carry circuit. In this paper we propose some optimizations in applying Dijk et.al.'s encryption system to securely compare two numbers. We also applied this optimized solution in preserving privacy in association rule mining (ARM) in two-party settings. We have further enhanced the two party secure association rule mining technique proposed by Kaosar et.al. The performance analysis shows that this proposed solution achieves a significant improvement.