arXiv Computation and Language September 21, 2026 By Shuo Huang, Gholamreza Haffari, Xingliang Yuan, Ting Yu, Lizhen Qu

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

Read the original on arXiv Computation and Language →

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.

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 Computation and Language.

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 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 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 AI

Jun 6

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

arXiv:2509. 20324v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with external document retrieval to produce more accurate and grounded responses.

By Atousa Arzanipour, Rouzbeh Behnia, Reza Ebrahimi, Kaushik Dutta

llms rag nlp 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

Aug 11

Mind the Hook: Source-Level Auditing of Privacy Defenses in Retrieval-Augmented Generation

arXiv:2608. 09001v1 Announce Type: cross Abstract: Black-box privacy scores for retrieval-augmented generation (RAG) are difficult to interpret unless the audited defense's active pipeline hook is known.

By Yanhang Li, Zhichao Fan, Zexin Zhuang

rag benchmarks safety

One email a morning, machine-written

Related stories

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

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

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

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data

Mind the Hook: Source-Level Auditing of Privacy Defenses in Retrieval-Augmented Generation