ATTAXONOMY: Unpacking Differential Privacy Guarantees Against Practical Adversaries

arXiv:2405.01716v1 Announce Type: new
Abstract: Differential Privacy (DP) is a mathematical framework that is increasingly deployed to mitigate privacy risks associated with machine learning and statistical analyses. Despite the growing adoption of DP, its technical privacy parameters do not lend themselves to an intelligible description of the real-world privacy risks associated with that deployment: the guarantee that most naturally follows from the DP definition is protection against membership inference by an adversary who knows all but one data record and …

adoption adversaries arxiv cs.cr cs.cy differential privacy framework machine machine learning privacy privacy risks real risks technical unpacking world world privacy