The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |