arXiv:2606. 06784v1 Announce Type: cross Abstract: Public social media posts can reveal private information through weak cues scattered across text, images, or metadata.
Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. However, Multi-modal Large Language Models (MLLMs), which process both text and images, introduce unique privacy challenges that remain underexplored.
The paper investigates whether inexpensive spectral metrics from the heavy‑tailed self‑regularisation framework can predict membership inference attack (MIA) vulnerability, offering a scalable alternative to costly shadow‑model attacks. Experiments on image and tabular classification tasks show that stable rank correlates positively with overall MIA success, while Log alpha‑Norm correlates negatively with MIA risk in low false‑positive regimes, outperforming conventional generalisation gap measures. These findings suggest that neural network spectra contain privacy leakage signals not captured by traditional overfitting metrics, pointing to spectral analysis as a promising direction for privacy auditing.
arXiv:2606. 09125v1 Announce Type: cross Abstract: Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information.
arXiv:2608.28691v1 Announce Type: cross Abstract: Wearable VLM pipelines promise continuous multimodal assistance from egocentric visual capture: a user asks a task-driven question about the surround...
arXiv:2607. 02897v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong capabilities, but they may memorize private information from web data, raising privacy concerns.
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:2607. 22695v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment.
arXiv:2606. 24623v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts.
The paper investigates whether large, instruction‑following Vision‑Language Models (VLMs) can reliably perform zero‑shot image privacy classification. It compares three open‑source VLMs to specialized privacy models on two public benchmarks, evaluating accuracy, robustness to image degradations (compression, lighting changes, noise), inference speed, and parameter count. The findings show that while VLMs remain robust to perturbations, they are less accurate and significantly slower than smaller, purpose‑built privacy models, indicating that scaling alone does not guarantee effective privacy classification.
arXiv:2508. 09105v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Language Models (LLMs) by introducing external knowledge sources.
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.
The paper introduces a clinically grounded privacy evaluation framework for medical language models, assessing leakage across a spectrum of adversarial access levels—from publicly inferable demographics to leaked note fragments. Using this framework on an LM pretrained on 378,000 clinical notes, the authors find that routine encounter metadata leads to high verbatim memorization and significant recovery of sensitive diagnoses (e.g., AUROC 0.91 for abortion, 0.82 for HIV). They also note that exact-match memorization can overstate disclosure, with 36% of memorized tokens being templated documentation, underscoring the risks of training on longitudinal clinical data and offering a reusable evaluation tool.