Using unknowns to prevent discovery of association rules
Download
Author
Yücel Saygin, Vassilios S. Verykios, Chris Clifton
Entry type
article
Abstract
Data mining technology has given us new capabilities to identify correlations in large data sets. This introduces risks when the data is to be made public, but the correlations are private. We introduce a method for selectively removing individual values from a database to prevent the discovery of a set of rules, while preserving the data for other applications. The efficacy and complexity of this method are discussed. We also present an experiment showing an example of this methodology.
Download
Date
2001 – 12
Journal
ACM SIGMOD Record
Key alpha
Clifton
Number
4
Pages
45-54
Publisher
ACM
Volume
30
Publication Date
2001-12-01