Paper 2016/1134

Privacy-preserving Hybrid Recommender System

Qiang Tang and Husen Wang

Abstract

Privacy issues in recommender systems have attracted the attention of researchers for many years. So far, a number of solutions have been proposed. Unfortunately, most of them are far from practical as they either downgrade the utility or are very inefficient. In this paper, we aim at a more practical solution (particularly in the sense of relieving the tension between utility and privacy), by proposing a privacy-preserving hybrid recommender system which consists of an incremental matrix factorization (IMF) component and a user-based collaborative filtering (UCF) component. The IMF component provides the fundamental utility while allows the service provider to efficiently learn feature vectors in plaintext domain, and the UCF component improves the utility while allows users to carry out their computations in an offline manner. Leveraging somewhat homomorphic encryption (SWHE) schemes, we provide privacy-preserving candidate instantiations for both components. Interestingly, as a side effect of the hybrid design, individual components can enhance each other's privacy guarantees. With respect to efficiency, our experiments demonstrate that the hybrid solution is much more efficient than existing solutions.