Social-K: Real-time K-anonymity guarantees for social network applications

Traditional approaches to K-anonymity provide privacy guarantees over publicly released data sets with specified quasi-identifiers. However, the most common public releases of personal data are now done through social networks and their APIs, which do not fit the previous research-centric data set release model, nor do they allow for clear assumptions about quasi-identifiers. This paper proposes a new definition of K-anonymity that suggests a practical way in which social networks could provide privacy guarantees to users of their API. To support as wide a range of applications as possible, the proposed privacy guarantee assumes all social-networking data may be a quasi-identifier and does not assume that data may be generalized and still be useful. Using the Facebook social networking API, we implement an application to demonstrate that providing such guarantees in real-time is feasible for real social networking data.

I. Introduction

Every month at least 250 million Facebook users release their personal social networking data through Facebook's API. The recipients of this data include over 500,000 social networking applications, 80,000 external websites, 65 million mobile devices, and 180 mobile operators [1]. Due to the nature of how this data is used and accessed, the traditional definition of -anonymity and how it is implemented does not apply to this public release of personal data. This paper suggests an alternative approach to -anonymity that directly applies to this data and how it is accessed.