Privacy-Preserving Friend Recommendation in an Integrated Social Environment

Ubiquitous Online Social Networks (OSN)s play a vital role in information creation, propagation and consumption. Given the recent multiplicity of OSNs with specially accumulated knowledge, integration partnerships are formed (without regard to privacy) to provide an enriched, integrated and personalized social experience. However, given the increasing privacy concerns and threats, it is important to develop methods that can provide collaborative capabilities while preserving user privacy. In this work, we focus on friend recommendation systems (FRS) for such partnered OSNs. We identify the various ways through which privacy leaks can occur, and propose a comprehensive solution that integrates both Differential Privacy and Secure Multi-Party Computation to provide a holistic privacy guarantee. We analyze the security of the proposed approach and evaluate the proposed solution with real data in terms of both utility and computational complexity.