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.
QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group Recovery
QuasiLeak-Bench is a new benchmark that evaluates large language model (LLM) based privacy detectors on their ability to recover quasi‑evidence groups—sets of weak quasi‑identifiers that jointly reveal private attributes—while respecting sender‑specified disclosure policies. The benchmark uses a reverse‑construction pipeline to generate documents containing verified quasi‑evidence groups and applies automated quality control to produce reliable ground truth at scale. Experiments show that current privacy detectors perform poorly on this task, but a fine‑tuned 4B LLM can outperform the best prompted models, indicating the task is learnable.
Related stories
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.
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.
arXiv Machine Learning
Sep 17
QuanText: Protecting Dataset-Level Secrets in Textual Data Sharing
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.
arXiv Machine Learning
Oct 2
PrivCert: Certifying Statement Support under Differential Privacy
arXiv:2609.38934v1 Announce Type: cross Abstract: Differentially private (DP) text generation can protect individual records, but privacy alone does not specify what evidence a released statement car...
arXiv Machine Learning
Aug 5
DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents
arXiv:2608. 03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly.
arXiv Machine Learning
Sep 1
On the Recoverability of Private Information Unlearning in Large Language Models
arXiv:2608.29943v1 Announce Type: new Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to re...
Hugging Face Trending Papers
Jun 22
Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models
Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks, but existing studies mainly focus on whether specific samples or sample-based data units are used for training.
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.
arXiv AI
Jun 18
TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction
arXiv:2606. 18996v1 Announce Type: cross Abstract: Agents are increasingly deployed in document-intensive workflows where sensitive private information is not an edge case but a routine input, e.
arXiv Computation and Language
4d ago
Exploring The Empirical Privacy Landscape of Synthetic Data
The paper compares data-level and training-level methods for balancing language model capability and privacy leakage on synthetic medical records with embedded canaries. Direct finetuning achieves the highest capability but leaks the most private information, while DP‑SGD reduces leakage at a significant cost to performance. Generating privacy‑aware synthetic data—especially with uniqueness‑aware rewriting—offers a better trade‑off, and more capable rewriting models tend to lower downstream privacy risks, though gains are inconsistent with increased compute.
arXiv Machine Learning
Sep 11
SoK: Privacy Attacks on Machine Learning via Explainable AI
The paper surveys 25 studies that use explainable AI to compromise machine learning models, covering attacks such as model extraction, membership inference, and model inversion. It distinguishes between how explanations are obtained—through target releases, attacker-derived methods, secondary disclosure, privileged access, or global artifacts—and shows that explanations can lower extraction costs and reveal membership signals via statistics, recourse distance, and robustness. The authors compare threat models, signals, and defenses, concluding that no single explanation type is always unsafe and that protection must be tailored to the specific acquisition path and target asset.