Pith. sign in

REVIEW

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.15349 v1 pith:HQYJ7Z2P submitted 2025-06-18 cs.LG cs.CR

classification cs.LGcs.CR
keywords auditingboundsone-rundp-sgdprivacywhileworkapproaches
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Pith tools