arXiv Machine Learning October 16, 2026 By Mathieu Dagr\'eou, Valentin Dorseuil, Mohammad Yaghini, Nicolas Papernot, Aur\'elien Bellet

Detectability without Interference: Efficient Canary Design for Privacy Auditing in One Run

Read the original on arXiv Machine Learning →

The paper introduces IBIS, a framework for designing canaries that are efficient for one‑run privacy auditing. IBIS optimizes each canary’s membership inference attack score while minimizing interference among canaries by encouraging orthogonality in embedding space. The method uses influence‑based greedy initialization and a bilevel optimization algorithm that updates a single model incrementally, achieving better performance‑cost trade‑offs and reducing computational cost by up to two orders of magnitude compared to existing approaches.

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 Machine Learning.

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 Machine Learning

Sep 23

Optimizing Canaries for Privacy Auditing with Metagradient Descent

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

computer-vision safety

arXiv AI

Jun 10

Advancing the State-of-the-Art in Empirical Privacy Auditing

arXiv:2606. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.

By Nicole Mitchell, Galen Andrew, Arun Ganesh, Brendan McMahan, Peter Kairouz

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jun 15

Let's Ask Gauss: Improved One-Run Privacy Auditing

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

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

Jun 24

Natural Identifiers for Privacy and Data Audits in Large Language Models

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

llms safety

One email a morning, machine-written

Related stories

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

Optimizing Canaries for Privacy Auditing with Metagradient Descent

Advancing the State-of-the-Art in Empirical Privacy Auditing

Let's Ask Gauss: Improved One-Run Privacy Auditing

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

Natural Identifiers for Privacy and Data Audits in Large Language Models