arXiv Machine Learning September 17, 2026 By Shuaiqi Wang, Zinan Lin, Giulia Fanti

QuanText: Protecting Dataset-Level Secrets in Textual Data Sharing

Read the original on arXiv Machine Learning →

QuanText is a training‑free, large‑language‑model‑agnostic mechanism for releasing textual datasets that protects dataset‑level secrets such as the proportion of records with a particular diagnosis or gender. It perturbs both the secret distribution and correlated attribute distributions by selecting candidate release distributions close to the private empirical distribution and rewriting each text sample to match the chosen distribution using attribute‑related snippets. The method is inspired by the Statistic Maximal Leakage framework and, under idealized conditions, satisfies an SML guarantee, while empirical evaluations show a superior privacy‑utility trade‑off compared to existing data generation baselines.

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

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

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 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 9

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

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.

By Bart{\l}omiej Marek, Lorenzo Rossi, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch, Adam Dziedzic

llms fine-tuning benchmarks 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

arXiv Machine Learning

Aug 27

Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models

The paper examines how supervised fine-tuning (SFT) of large language models can leak personally identifiable information (PII) when the fine-tuning data contains user-provided sensitive details. It introduces COVA, a coverage-aware decoding algorithm that improves targeted PII reconstruction from SFT models, especially when an adversary has limited contextual knowledge about a target. Experiments on medical and legal Q&A datasets show that even small proprietary SFT datasets can lead to significant privacy leakage via PII reconstruction.

By Sae Furukawa, Alina Oprea

llms fine-tuning safety

One email a morning, machine-written

Related stories

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

Natural Identifiers for Privacy and Data Audits in Large Language Models

Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

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

Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models