arXiv AI July 22, 2026 By Kareem Amin, Rudrajit Das, Alessandro Epasto, Adel Javanmard, Dennis Kraft, M\'onica Ribero, Sergei Vassilvitskii

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

Read the original on arXiv AI →

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.

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.

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 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

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

arXiv Machine Learning

Jun 5

Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Data

arXiv:2606. 06334v1 Announce Type: new Abstract: Counterfactuals are typically used in high-stakes decision areas to explain a machine learning model by showing how changes to the user profiles result in the desired outcome.

By Maryam Babaei, Yingke Wang, Hadrien Lautraite, Heber H. Arcolezi, Ulrich Aivodji, Sebastien Gambs

safety

arXiv Machine Learning

1d ago

Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective

The paper argues that evaluating anonymity in synthetic data generation must focus on the generative model rather than just the resulting dataset. It interprets GDPR definitions of personal data and anonymization under realistic model-access scenarios, mapping these to state‑of‑the‑art privacy attacks. The authors conclude that synthetic data alone is insufficient for anonymization, and that Differential Privacy offers stronger protection than Similarity‑based Privacy Metrics.

By Georgi Ganev, Emiliano De Cristofaro

benchmarks safety

One email a morning, machine-written

Related stories

Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data

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

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

Natural Identifiers for Privacy and Data Audits in Large Language Models

Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Data

Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective