CryptoRec: Secure Recommendations as a Service

Recommender systems rely on large datasets of historical data and entail serious privacy risks. A server offering recommendations as a service to a client might leak more information than necessary regarding its recommendation model and training dataset. At the same time, the disclosure of the client’s preferences to the server is also a matter of concern. Providing recommendations while preserving privacy in both senses is a difficult task, which often comes into conflict with the utility of the system in terms of its recommendation-accuracy and efficiency. Widely-purposed cryptographic primitives such as secure multi-party computation and homomorphic encryption offer strong security guarantees, but in conjunction with state-ofthe-art recommender systems yield far-from-practical solutions. We precisely define the above notion of security and propose CryptoRec, a novel recommendations-as-a-service protocol, which encompasses a crypto-friendly recommender system. This model possesses two interesting properties: (1) It models useritem interactions in a user-free latent feature space in which it captures personalized user features by an aggregation of item features. This means that a server with a pre-trained model can provide recommendations for a client without having to re-train the model with the client’s preferences. Nevertheless, re-training the model still improves accuracy. (2) It only uses addition and multiplication operations, making the model straightforwardly compatible with homomorphic encryption schemes. We demonstrate the utility of CryptoRec on three realworld datasets. Results show that the accuracy and efficiency performance of CryptoRec stand up to state-of-the-art recommender systems. In fact, CryptoRec is able to predict a client’s preferences for more than 500 items per seconds on a regular laptop in a fully-private manner, while its predictions incur only a little accuracy loss (or none at all, depending on the dataset) when compared to state-of-the-art recommender systems computing over clear data.