Privacy enhanced recommender system
Zekeriya Erkin, Michael Beye, Thijs Veugen, Reginald L. Lagendijk · TNO Repository · 2010
Recommender systems are widely used in online applications since they enable personalized service to the users. The underlying collaborative filtering techniques work on user’s data which are mostly privacy sensitive and can be misused by the service provider. To protect the privacy of the users, we propose to encrypt the privacy sensitive data and generate recommendations by processing them under encryption. With this approach, the service provider learns no information on any user’s preferences or the recommendations made. The proposed method is based on homomorphic encryption schemes and secure multiparty computation (MPC) techniques. The overhead of working in the encrypted domain isminimized by packing data as shown in the complexity analysis.