ASSOCIATION RULE HIDING OVER DATA STREAMS

Abstract

Association rule mining is used in various applications. Also information systems may need to take privacy issues into account when releasing data to outside parties. Due to recent advances, releasing data to other parties may be done in a streaming fashion. In this paper, we introduce a new system in which association rule mining over data streams and association rule hiding for traditional databases are merged. The stream association rule hiding algorithm presented can be applied on both raw data and template guided XML data. The algorithms presented are implemented and tested.