The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Annamalai, Meenatchi Sundaram Muthu Selva, Balle, Borja, Hayes, Jamie, Kaissis, Georgios, De Cristofaro, Emiliano
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918245154422784
author Annamalai, Meenatchi Sundaram Muthu Selva
Balle, Borja
Hayes, Jamie
Kaissis, Georgios
De Cristofaro, Emiliano
author_facet Annamalai, Meenatchi Sundaram Muthu Selva
Balle, Borja
Hayes, Jamie
Kaissis, Georgios
De Cristofaro, Emiliano
contents In this paper, we systematize research on auditing Differential Privacy (DP) techniques, aiming to identify key insights and open challenges. First, we introduce a comprehensive framework for reviewing work in the field and establish three cross-contextual desiderata that DP audits should target -- namely, efficiency, end-to-end-ness, and tightness. Then, we systematize the modes of operation of state-of-the-art DP auditing techniques, including threat models, attacks, and evaluation functions. This allows us to highlight key details overlooked by prior work, analyze the limiting factors to achieving the three desiderata, and identify open research problems. Overall, our work provides a reusable and systematic methodology geared to assess progress in the field and identify friction points and future directions for our community to focus on.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16666
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing
Annamalai, Meenatchi Sundaram Muthu Selva
Balle, Borja
Hayes, Jamie
Kaissis, Georgios
De Cristofaro, Emiliano
Cryptography and Security
Machine Learning
In this paper, we systematize research on auditing Differential Privacy (DP) techniques, aiming to identify key insights and open challenges. First, we introduce a comprehensive framework for reviewing work in the field and establish three cross-contextual desiderata that DP audits should target -- namely, efficiency, end-to-end-ness, and tightness. Then, we systematize the modes of operation of state-of-the-art DP auditing techniques, including threat models, attacks, and evaluation functions. This allows us to highlight key details overlooked by prior work, analyze the limiting factors to achieving the three desiderata, and identify open research problems. Overall, our work provides a reusable and systematic methodology geared to assess progress in the field and identify friction points and future directions for our community to focus on.
title The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2506.16666