Privacy-preserving Collaborative Filtering Using Randomized Response

• Kikuchi Hiroaki

  Department of Frontier Media Science, School of Interdisciplinary Mathematical Sciences, Meiji University School of Information and Telecommunication Engineering, Tokai University

• Mochizuki Anna

  Graduate School of Science and Technology, Tokai University

Abstract

This paper proposes a new privacy-preserving recommendation method classified into a randomized perturbation scheme in which a user adds a random noise to the original rating value and a server provides a disguised data to allow users to predict the rating value for unseen items. The proposed scheme performs a perturbation in a randomized response scheme, which preserves a higher degree of privacy than that of an additive perturbation. To address the accuracy reduction of the randomized response, the proposed scheme uses a posterior probability distribution function, derived from Bayes' estimation for the reconstruction of the original distribution, to revise the similarity between items computed from the disguised matrix. A simple experiment shows the accuracy improvement of the proposed scheme.

Journal

• Information and Media Technologies

  Information and Media Technologies 8 (4), 1217-1223, 2013

  Information and Media Technologies Editorial Board

Keywords

• collaborative filtering
• privacy-preserving data mining
• cryptographic protocol

Details

• CRID: 1390001205264293120
• NII Article ID: 130003384055
• DOI: 10.11185/imt.8.1217
• ISSN: 18810896
• Text Lang: en
• Data Source:
  • JaLC
  • CiNii Articles
• Abstract License Flag: Disallowed