arXiv AI October 21, 2026 By Valentin Dorseuil (DI-ENS), Meenatchi Sundaram Muthu Selva Annamalai (UCL), Jamal Atif (CMAP), Olivier Capp\'e (DI-ENS), Nicolas Papernot (Inria)

Reliable Estimation of Differential Privacy under Selection Bias

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

safety

arXiv Machine Learning

Sep 1

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

arXiv:2608.28934v1 Announce Type: new Abstract: Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In...

By Saloni Modi, Srivi Balaji, Yusong Zhu, Gautam Kamath, Kevin Tian

benchmarks safety

arXiv Machine Learning

2d ago

Shift-aware score transport for privacy auditing without retraining

The paper introduces a shift‑aware score transport method for privacy auditing that does not require retraining the target model. It estimates the in‑distribution non‑member score distribution from out‑of‑distribution data, transports this relationship to the target covariate distribution, and applies a conservative correction to account for potential extrapolation errors. Experiments on multiple datasets with distribution shifts show that the method provides more stable privacy estimates while maintaining tighter lower bounds than existing baselines.

By Yaohong Yang, Gauri Pradhan, Qi Chen, Samuel Kaski, Antti Honkela

safety

arXiv AI

Jul 22

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data

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

llms safety

arXiv AI

Jun 16

Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data

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

llms safety

arXiv Machine Learning

Jun 5

Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run

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

rag safety

arXiv AI

Jul 17

Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms

arXiv:2607. 14607v1 Announce Type: cross Abstract: Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees.

By Umid Suleymanov, Ilhama Novruzova, Khalid Mammadov, Natavan Hasanova, Murat Kantarcioglu

safety

One email a morning, machine-written

Related stories

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

Shift-aware score transport for privacy auditing without retraining

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data

Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data

Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run

Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms