# Tight Privacy Audit in One Run

arXiv: https://arxiv.org/abs/2509.08704 · HTML: https://mlsanity.com/paper/2509.08704/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2025.

## Built on by (most cited first, 2 of 2)

- [Let's Ask Gauss: Improved One-Run Privacy Auditing](https://mlsanity.com/paper/2606.12733/) (2026)
- [Calibrating One-Round Membership Inference with Neighbors](https://mlsanity.com/paper/2609.36331/) (2026)

## Abstract (arXiv)

In this paper, we study the problem of privacy audit in one run and show that our method achieves tight audit results for various differentially private protocols. This includes obtaining tight results for auditing (varepsilon,δ)-DP algorithms where all previous work fails to achieve in any parameter setups. We first formulate a framework for privacy audit textitin one run with refinement compared with previous work. Then, based on modeling privacy by the f-DP formulation, we study the implications of our framework to obtain a theoretically justified lower bound for privacy audit. In the experiment, we compare with previous work and show that our audit method outperforms the rest in auditing various differentially private algorithms. We also provide experiments that give contrasting conclusions to previous work on the parameter settings for privacy audits in one run. Our implementation is at https://github.com/zihangxiang/tight-privacy-audit-in-one-run.git