Data mining technology has given us new capabilities to identify correlatio
ns in large data sets. This introduces risks when the data is to be made pu
blic, but the correlations are private. We introduce a method for selective
ly removing individual values from a database to prevent the discovery of a
set of rules, while preserving the data for other applications. The effica
cy and complexity of this method are discussed. We also present an experime
nt showing an example of this methodology.