Perturbation-Based Private Profile Matching in Social Networks

Abstract

Social networking has become part of our life in recent years, allowing users to converse and connect with people sharing similar interests in real world. However, networking via the social media suffers from serious privacy issues, and one of which is profile attribute leakage in friend discovery. While existing studies mainly focus on leveraging rich cryptographic algorithms to prevent privacy leak, we propose a novel perturbation-based private profile matching mechanism by mixing the private data with random noise to preserve privacy in this paper. In this paper, we consider the case where the profiles are fine-grained, meaning that each attribute is associated with a user-specific numerical value to indicate the level of interest. By carefully tuning the amount of information owned by each party, we guarantee that privacy is effectively preserved while the matching result of users’ profiles can be cooperatively obtained. We first give an introduction to a basic scheme, then detail two improved ones by, respectively, taking collusion attack and verifiability into consideration. As no expensive encryption algorithms get involved, our methods are computationally efficient; thus they are more practical for real-world applications. Theoretical security analysis as well as comparison-based simulation studies are carried out to evaluate the performance of our designs.