An Architecture for Privacy-preserving Mining of Client Information

Kantarcioglu, M. and Vaidya, J.

Due to privacy concerns, clients of some services may not want to reveal their private information. Even in these situations, data mining is feasible without sacrificing user privacy. Prior approaches to this problem generally trade off accuracy for security, without giving provable bounds on security. Alternatives to the randomization technique are required to enable accurate data mining while strictly preserving privacy. In this paper, we present a general architecture that enables privacy-preserving mining of client information. Under some reasonable assumptions, we show that our methods are secure, while maintaining the accuracy of the results.

Cite as: Kantarcioglu, M. and Vaidya, J. (2002). An Architecture for Privacy-preserving Mining of Client Information. In Proc. IEEE ICDM Workshop on Privacy, Security and Data Mining (PSDM 2002), Maebashi City, Japan. CRPIT, 14. Clifton, C. and Estivill-Castro, V., Eds. ACS. 37-42.

(from crpit.com) (local if available)