Paper 2015/364 Original: eprint.iacr.org/2015/364 ↗

Privacy-preserving Context-aware Recommender Systems: Analysis and New Solutions

Abstract

Nowadays, recommender systems have become an indispensable part of our daily life and provide personalized services for almost everything. However, nothing is for free -- such systems have also upset the society with severe privacy concerns because they accumulate a lot of personal information in order to provide recommendations. In this work, we construct privacy-preserving recommendation protocols by incorporating cryptographic techniques and the inherent data characteristics in recommender systems. We first revisit the protocols by Jeckmans et al. at ESORICS 2013 and show a number of security and usability issues. Then, we propose two privacy-preserving protocols, which compute predicted ratings for a user based on inputs from both the user's friends and a set of randomly chosen strangers. A user has the flexibility to retrieve either a predicted rating for an unrated item or the Top-N unrated items. The proposed protocols prevent information leakage from both protocol executions and the protocol outputs: a somewhat homomorphic encryption scheme is used to make all computations run in encrypted form, and inputs from the randomly-chosen strangers guarantee that the inputs of a user's friends will not be compromised even if this user's outputs are leaked. Finally, we use the well-known MovieLens 100k dataset to evaluate the performances for different parameter sizes.