ENBIS-17 in Naples

9 – 14 September 2017; Naples (Italy) Abstract submission: 21 November 2016 – 10 May 2017

The Fienberg Effect and the Promise of Private Social Network Analysis

11 September 2017, 13:00 – 13:30

Abstract

Submitted by
Aleksandra Slavkovic
Authors
Aleksandra Slavkovic (Penn State University)
Abstract
In the area of data privacy and confidentiality, Stephen Fienberg has been a key player in bringing computer scientists and statisticians to work together. His contributions to methodology of disclosure limitation and their impact to a more general problem of privacy protection and confidentiality will be discussed. In the spirit of Steve's interdisciplinary work and motivated by a real-life problem of sharing social network data that contain sensitive personal information, we propose a novel approach to release and analyze synthetic graphs in order to protect privacy of individual relationships captured by the social network while maintaining the validity of statistical results. We use a simple yet effective randomized response mechanism to generate synthetic networks under ε-edge differential privacy offering formal privacy guarantees, and then use likelihood based inference for missing data and Markov chain Monte Carlo techniques to fit exponential-family random graph models to the generated synthetic networks. This promises reproducibility of existing studies and discovery of new scientific insights that can be obtained by analyzing such data. (Joint work with V. Karwa and P. Krivitsky).

Return to programme