Secure Two-Party Association Rule Mining Based on One-pass FP-Tree

Golam Kaosar, Yi. Xun

Research output: Contribution to journalArticle

Abstract

Frequent Path tree (FP-tree) is a popular method to compute association rules and is faster than Aprioribased solutions in some cases. Association rule mining using FP-tree method cannot ensure entire privacy since frequency of the itemsets are required to share among participants at the first stage. Moreover, FP-tree method requires two scans of database transactions which may not be the best solution if the database is very large or the database server does not allow multiple scans. In addition, one-pass FP-tree can accommodate continuous or periodically changing databases without restarting the process as opposed to a regular FP-tree based solution. In this paper, the authors propose a one-pass FP-tree method to perform association rule mining without compromising any data privacy among two parties. A fully homomorphic encryption system over integer numbers is applied to ensure secure computation among two data sites without disclosing any number belongs to themselves.
Original languageEnglish
Pages (from-to)13-32
Number of pages20
JournalInternational Journal of Information Security and Privacy
Volume5
Issue number2
DOIs
Publication statusPublished - Apr 2011

Fingerprint Dive into the research topics of 'Secure Two-Party Association Rule Mining Based on One-pass FP-Tree'. Together they form a unique fingerprint.

  • Cite this