Score: 1

Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference

Published: June 18, 2025 | arXiv ID: 2506.15349v1

By: Terrance Liu , Matteo Boglioni , Yiwei Fu and more

Potential Business Impact:

Checks computer privacy without needing many tries.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

Differential privacy (DP) auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many training runs that are prohibitively costly, recent work introduces one-run auditing approaches that effectively audit DP-SGD in white-box settings while still being computationally efficient. However, in the more practical black-box setting where gradients cannot be manipulated during training and only the last model iterate is observed, prior work shows that there is still a large gap between the empirical lower bounds and theoretical upper bounds. Consequently, in this work, we study how incorporating approaches for stronger membership inference attacks (MIA) can improve one-run auditing in the black-box setting. Evaluating on image classification models trained on CIFAR-10 with DP-SGD, we demonstrate that our proposed approach, which utilizes quantile regression for MIA, achieves tighter bounds while crucially maintaining the computational efficiency of one-run methods.

Country of Origin
πŸ‡ΊπŸ‡Έ πŸ‡¨πŸ‡­ United States, Switzerland

Page Count
8 pages

Category
Computer Science:
Machine Learning (CS)