On the (Im)possibility of Preserving Utility and Privacy in Personalized Social Recommendations

TL;DR

This paper investigates the trade-off between privacy and utility in social recommendation systems, establishing theoretical bounds and proposing algorithms to achieve differential privacy, revealing limitations and feasibility conditions.

Contribution

It provides lower bounds on utility loss for differentially private social recommendation algorithms and introduces two algorithms with analyzed performance.

Findings

Good private recommendations are feasible only for some users or with lenient privacy settings.

The proposed algorithms approach the theoretical lower bounds in certain scenarios.

Strong privacy constraints significantly impact recommendation utility.

Abstract

With the recent surge of social networks like Facebook, new forms of recommendations have become possible -- personalized recommendations of ads, content, and even new social and product connections based on one's social interactions. In this paper, we study whether "social recommendations", or recommendations that utilize a user's social network, can be made without disclosing sensitive links between users. More precisely, we quantify the loss in utility when existing recommendation algorithms are modified to satisfy a strong notion of privacy called differential privacy. We propose lower bounds on the minimum loss in utility for any recommendation algorithm that is differentially private. We also propose two recommendation algorithms that satisfy differential privacy, analyze their performance in comparison to the lower bound, both analytically and experimentally, and show that good private social recommendations are feasible only for a few users in the social network or for a lenient setting of privacy parameters.