Privacy-preserving frequent pattern sharing

Authors:
Zhihui Wang;Wei Wang;Baile Shi;S. H. Boey
Affiliations:
Department of Computing and Information Technology, Fudan University, Shanghai, China;Department of Computing and Information Technology, Fudan University, Shanghai, China;Department of Computing and Information Technology, Fudan University, Shanghai, China;Gentec Pte Ltd, Singapore
Venue:
DASFAA'07 Proceedings of the 12th international conference on Database systems for advanced applications
Year:
2007

Citing 9
Cited 0

Data mining: concepts and techniques

Data mining: concepts and techniques
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
Using unknowns to prevent discovery of association rules

ACM SIGMOD Record
Fast Algorithms for Mining Association Rules in Large Databases

VLDB '94 Proceedings of the 20th International Conference on Very Large Data Bases
Disclosure Limitation of Sensitive Rules

KDEX '99 Proceedings of the 1999 Workshop on Knowledge and Data Engineering Exchange
Computational complexity of itemset frequency satisfiability

PODS '04 Proceedings of the twenty-third ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Preserving Private Knowledge in Frequent Pattern Mining

ICDMW '06 Proceedings of the Sixth IEEE International Conference on Data Mining - Workshops
k-anonymous patterns

PKDD'05 Proceedings of the 9th European conference on Principles and Practice of Knowledge Discovery in Databases
An effective approach for hiding sensitive knowledge in data publishing

WAIM '06 Proceedings of the 7th international conference on Advances in Web-Age Information Management

Quantified Score

Hi-index	0.00

Visualization

Abstract

Some of the knowledge discovered by data mining may contain sensitive information, which should be hidden before sharing the result of data mining. In this paper, we consider that the knowledge for sharing is discovered by frequent pattern mining, and some of the frequent patterns are private, which cannot be shared. Our problem of privacy-preserving frequent pattern sharing is to hide these private patterns before sharing the result of frequent pattern mining, and at the same time maximize the number of non-private frequent patterns to be shared. We show that this problem is NP-hard, and present three item-based pattern sanitization algorithms for transforming the result of frequent pattern mining into a privacy-free frequent pattern set.