Statistical Quantification of Differential Privacy: A Local Approach
This work addresses the challenge of privacy validation for practitioners, offering a user-friendly method to estimate privacy parameters, though it is incremental in improving upon existing statistical techniques.
The authors tackled the problem of quantifying differential privacy for black-box algorithms by introducing a new statistical approach that avoids event selection, resulting in estimators and confidence intervals with fast convergence rates and asymptotic validity.
In this work, we introduce a new approach for statistical quantification of differential privacy in a black box setting. We present estimators and confidence intervals for the optimal privacy parameter of a randomized algorithm $A$, as well as other key variables (such as the "data-centric privacy level"). Our estimators are based on a local characterization of privacy and in contrast to the related literature avoid the process of "event selection" - a major obstacle to privacy validation. This makes our methods easy to implement and user-friendly. We show fast convergence rates of the estimators and asymptotic validity of the confidence intervals. An experimental study of various algorithms confirms the efficacy of our approach.