Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
Sequential Auditing for f-Differential Privacy
Tim Kutta, Martin Dunsche, Yu Wei +1
We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and imp…
cs.CR2025
General-Purpose -DP Estimation and Auditing in a Black-Box Setting
Önder Askin, Holger Dette, Martin Dunsche +4
In this paper we propose new methods to statistically assess -Differential Privacy (-DP), a recent refinement of differential privacy (DP) that remedies certain weaknesses of…
cs.CR2023
The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning
Yu Wei, Yun Lu, Malik Magdon-Ismail +1
We investigate the privacy of {\em any} algorithm whose outputs have Gaussian distribution. This work is motivated by the prevalence of such algorithms in several useful (ML) appli…