arXiv Machine Learning June 9, 2026 By Bart{\l}omiej Marek, Lorenzo Rossi, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch, Adam Dziedzic

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

Read the original on arXiv Machine Learning →

arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.

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 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 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

arXiv Computation and Language

Sep 21

Conformal Privacy Auditing: Calibrated Re-identification Attacks with Statistical Guarantees

Conformal Privacy Auditing (CPA) is a distribution‑free framework that calibrates re‑identification risk for each released document against large language model (LLM)‑empowered adversaries. It outputs a conformal ambiguity set of candidate identities that is guaranteed to contain the true identity with a user‑chosen confidence level under exchangeability, along with an interpretable leakage proxy derived from the set size. CPA supports both logit‑access and sampling‑only attackers, enabling audits of both open‑source and proprietary models, and demonstrates calibrated coverage across various benchmarks and attacker configurations.

By Shuo Huang, Gholamreza Haffari, Xingliang Yuan, Ting Yu, Lizhen Qu

llms benchmarks safety

arXiv Machine Learning

Jun 18

FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk

arXiv:2502. 17748v4 Announce Type: replace Abstract: Federated Learning (FL) inherently mitigates mass data centralization risks; however, its privacy protections are not equally distributed - leaving vulnerable individuals disproportionately exposed to sophisticated privacy attacks.

By Tianyu Zhao, Mahmoud Srewa, Salma Elmalaki

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 Machine Learning

Jul 21

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering

arXiv:2310. 16152v5 Announce Type: replace-cross Abstract: Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis.

By Md Rafi Ur Rashid, Vishnu Asutosh Dasu, Kang Gu, Najrin Sultana, Shagufta Mehnaz

llms nlp safety

One email a morning, machine-written

Related stories

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

Natural Identifiers for Privacy and Data Audits in Large Language Models

Conformal Privacy Auditing: Calibrated Re-identification Attacks with Statistical Guarantees

FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk

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

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering