paper-with-me

홈 › Papers

Sequential Auditing for f-Differential Privacy

2026-02-06 · Tim Kutta, Martin Dunsche, Yu Wei, Vassilis Zikas arxiv

We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and implementation bugs. Most existing auditors are batch-based or targeted toward the traditional notion of $(\varepsilon,δ)$-DP; typically both. In this work, we shift the focus to the highly expressive privacy concept of $f$-DP, in which the entire privacy behavior is captured by a single tradeoff curve. Our auditors detect violations across the full privacy spectrum with statistical significance guarantees, which are supported by theory and simulations. Most importantly, and in contrast to prior work, our auditors do not require a user-specified sample size as an input. Rather, they adaptively determine a near-optimal number of samples needed to reach a decision, thereby avoiding the excessively large sample sizes common in many auditing studies. This reduction in sampling cost becomes especially beneficial for expensive training procedures such as DP-SGD. Our method supports both whitebox and blackbox settings and can also be executed in one-run frameworks.

📄 PDF Abstract BibTeX arXiv:2602.06518

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sequentially Auditing Differential Privacy

2025-09-08 · Tomás González, Mateo Dulce-Rubio, Aaditya Ramdas, Mónica Ribero arxiv

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 er…

Tight Auditing of Differentially Private Machine Learning

2023-02-15 · Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle 외

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy …

Federated Learning

Debugging Differential Privacy: A Case Study for Privacy Auditing

2022-02-24 · Florian Tramer, Andreas Terzis, Thomas Steinke, Shuang Song 외

Differential Privacy can provide provable privacy guarantees for training data in machine learning. However, the presence of proofs does not preclude the presence of errors. Inspired by recent advances in auditing which …

Tight Auditing of Differential Privacy in MST and AIM

2026-04-20 · Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Bogdan Kulynych arxiv

State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarantees remains challenging. We introduce a Gaussian Differential Privacy …

Auditing $f$-Differential Privacy in One Run

2024-10-29 · Saeed Mahloujifar, Luca Melis, Kamalika Chaudhuri

Empirical auditing has emerged as a means of catching some of the flaws in the implementation of privacy-preserving algorithms. Existing auditing mechanisms, however, are either computationally inefficient requiring mult…

Privacy Preserving