Assessing Centrality Without Knowing Connections

TL;DR

This paper introduces a method for multiple distrustful parties to compute node influence in social networks using egocentric betweenness centrality while preserving privacy through differential privacy, with theoretical and empirical validation.

Contribution

It presents the first approach enabling privacy-preserving EBC computation across multiple parties without revealing internal network details.

Findings

Achieves low 1.07 relative error at privacy budget ε=0.1 on Facebook data.

Provides theoretical bounds on private EBC error with high probability.

Demonstrates scalability with increasing number of network providers.

Abstract

We consider the privacy-preserving computation of node influence in distributed social networks, as measured by egocentric betweenness centrality (EBC). Motivated by modern communication networks spanning multiple providers, we show for the first time how multiple mutually-distrusting parties can successfully compute node EBC while revealing only differentially-private information about their internal network connections. A theoretical utility analysis upper bounds a primary source of private EBC error---private release of ego networks---with high probability. Empirical results demonstrate practical applicability with a low 1.07 relative error achievable at strong privacy budget $\epsilon=0.1$ on a Facebook graph, and insignificant performance degradation as the number of network provider parties grows.