The paper investigates black-box privacy auditing for differentially private learning algorithms, focusing on DP‑SGD. It introduces a method that optimizes the auditor’s canary set using metagradient descent, improving empirical lower bounds on privacy parameters compared to prior canary designs. The approach is shown to be DP‑SGD agnostic and efficient, with optimized canaries for small models remaining effective for larger DP‑SGD models.
By Matteo Boglioni, Terrance Liu, Andrew Ilyas, Zhiwei Steven Wu
arXiv:2606. 16952v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
By Kareem Amin, Rudrajit Das, Alessandro Epasto, Adel Javanmard, Dennis Kraft, M\'onica Ribero, Sergei Vassilvitskii
arXiv:2606. 12733v2 Announce Type: replace Abstract: Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guarantees hold in practice.
By Adya Agrawal, Yu Wei, Jaspal Singh, Malik Magdon-Ismail, Vassilis Zikas
The paper extends the abstract gradient training (AGT) framework to provide tighter differential privacy guarantees for both private prediction and private learning. It introduces Abstract Gradient Sampling (AGS) to analyze privacy in continuous, unbounded regression and offers theoretical and empirical evidence that these methods yield tighter bounds than global-sensitivity baselines, even in previously unbounded settings. The authors also demonstrate that their private learning algorithm can outperform standard private learners under comparable conditions.
By Mihnea Ghitu, Matthew Wicker
The paper addresses a flaw in differential privacy audits where selection bias in Membership Inference Attacks leads to overestimated lower bounds on privacy leakage. By applying statistical correction methods, the authors demonstrate that uncorrected audits can violate theoretical privacy guarantees up to four times more often than claimed, while corrected audits maintain valid bounds at the nominal confidence level.
By Valentin Dorseuil (DI-ENS), Meenatchi Sundaram Muthu Selva Annamalai (UCL), Jamal Atif (CMAP), Olivier Capp\'e (DI-ENS), Nicolas Papernot (Inria)
arXiv:2606. 16952v1 Announce Type: cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
By Kareem Amin, Rudrajit Das, Alessandro Epasto, Adel Javanmard, Dennis Kraft, M\'onica Ribero, Sergei Vassilvitskii
arXiv:2605. 27292v2 Announce Type: replace Abstract: Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters.
By Mathieu Dagr\'eou, Aur\'elien Bellet
arXiv:2503. 10945v3 Announce Type: replace-cross Abstract: Current practices for reporting differential privacy (DP) guarantees for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture.
By Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis, Flavio P. Calmon, Jamie Hayes, Borja Balle, Antti Honkela
arXiv:2512. 04008v2 Announce Type: replace Abstract: Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model.
By Zo\"e Ruha Bell, Anvith Thudi, Olive Franzese-McLaughlin, Nicolas Papernot, Shafi Goldwasser
arXiv:2606. 24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges.
By Lorenzo Rossi, Bart{\l}omiej Marek, Franziska Boenisch, Adam Dziedzic
arXiv:2607. 16620v1 Announce Type: cross Abstract: Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems.
By Rakshit Naidu
arXiv:2606. 14518v1 Announce Type: new Abstract: The removal of learned data from Machine Learning models through Machine Unlearning (MU) has been widely studied; however, there has yet to be an agreed-upon scheme for auditing MU.
By Liou Tang, James Joshi, Ashish Kundu