Score: 2

Sequentially Auditing Differential Privacy

Published: September 8, 2025 | arXiv ID: 2509.07055v1

By: Tomás González , Mateo Dulce-Rubio , Aaditya Ramdas and more

BigTech Affiliations: Google

Potential Business Impact:

Checks if private data stays secret faster.

Business Areas:
A/B Testing Data and Analytics

We propose a practical sequential test for auditing differential privacy guarantees of black-box mechanisms. The test processes streams of mechanisms' outputs providing anytime-valid inference while controlling Type I error, overcoming the fixed sample size limitation of previous batch auditing methods. Experiments show this test detects violations with sample sizes that are orders of magnitude smaller than existing methods, reducing this number from 50K to a few hundred examples, across diverse realistic mechanisms. Notably, it identifies DP-SGD privacy violations in \textit{under} one training run, unlike prior methods needing full model training.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
30 pages

Category
Computer Science:
Cryptography and Security