From the information bottleneck to the privacy funnel

Nadia Fawaz
Senior researcher, Technicolor research center
Given on: May 8th, 2015

Abstract

We focus on the privacy-utility trade-off encountered by users who wish to disclose some information to an analyst, that is correlated with their private data, in the hope of receiving some utility. We rely on a general privacy statistical inference framework, under which data is transformed before it is disclosed, according to a probabilistic privacy mapping. We show that when the log-loss is introduced in this framework in both the privacy metric and the distortion metric, the privacy leakage and the utility constraint can be reduced to the mutual information between private data and disclosed data, and between non-private data and disclosed data respectively. We justify the relevance and generality of the privacy metric under the log-loss by proving that the inference threat under any bounded cost function can be upperbounded by an explicit function of the mutual information between private data and disclosed data. We then show that the privacy-utility tradeoff under the log-loss can be cast as the non-convex Privacy Funnel optimization, and we leverage its connection to the Information Bottleneck, to provide a greedy algorithm that is locally optimal. We evaluate its performance on the US census dataset. Finally, we characterize the optimal privacy mapping for the Gaussian Privacy Funnel.

Bio

Nadia Fawaz is a senior researcher at Technicolor research center in Los Altos, CA. Her current research interests include data privacy and personalization. Her work leverages techniques from information theory, random matrix theory, statistics and privacy theory, and aims at bridging theory and practice. From 2009 to 2011, she was a postdoctoral researcher in the Research Laboratory of Electronics (RLE) at the Massachusetts Institute of Technology (MIT), Cambridge, MA. She received her Ph.D. degree in 2008 and her Diplôme d’ingénieur (M.Sc.) in 2005 both in Electrical Engineering, from École Nationale Supérieure des Télécommunications de Paris and EURECOM, France. She is a Member of IEEE and of ACM. (contact: nadia.fawaz@technicolor.com)