Privacy-Preserving Decision Tree Classification over Horizontally Partitioned Data

Authors

Justin Zhan, School of Information Technology & Engineering, University of Ottawa, CanadaFollow
Stan Matwin, School of Information Technology & Engineering, University of Ottawa, CanadaFollow
LiWu Chang, Center For High Assurance Computer Systems, Naval Research Laboratory, USAFollow

Document Type

Article

Abstract

Protection of privacy is one of important problems in data mining. The unwillingness to share their data frequently results in failure of collaborative data mining. This paper studies how to build a decision tree classifier under the following scenario: a database is horizontally partitioned into multiple pieces, with each piece owned by a particular party. All the parties want to build a decision tree classifier based on such a database, but due to the privacy constraints, neither of them wants to disclose their private pieces. We build a privacy-preserving system, including a set of secure protocols, that allows the parties to construct such a classifier. We guarantee that the private data are securely protected.

Recommended Citation

Zhan, Justin; Matwin, Stan; and Chang, LiWu, "Privacy-Preserving Decision Tree Classification over Horizontally Partitioned Data" (2005). ICEB 2005 Proceedings (Hong Kong, SAR China). 70.
https://aisel.aisnet.org/iceb2005/70