Hugging Face Trending Papers June 23, 2026

Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients

Read the original on Hugging Face Trending Papers →

Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in healthcare, where patient medical images paired with clinical reports demand rigorous privacy safeguards.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

Hugging Face Trending Papers

Jun 24

Beyond Visual Forensics: Auditing Multimodal Robustness for Synthetic Medical Image Detection

With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored vision-language model (VLM)-based synthetic image detection, these evaluations typically consider images in isolation.

llms multimodal benchmarks

arXiv AI

Jul 2

Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection

arXiv:2606. 25375v2 Announce Type: replace-cross Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud.

By Ching-Hao Chiu, Hao-Wei Chung, Gelei Xu, Xueyang Li, Pin-Yu Chen, John Kheir, Meysam Ghaffari, Carlos Morato, Ahmed Abbasi, Yiyu Shi

llms multimodal benchmarks

arXiv Machine Learning

Jul 15

Reducing information dependency does not cause training data privacy. Adversarially non-robust features do

arXiv:2607. 12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks.

By Rasmus Torp, Shailen K. Smith, Adam Breuer

benchmarks safety

arXiv Machine Learning

Jul 16

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training

arXiv:2607. 13541v1 Announce Type: cross Abstract: To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image (T2I)-generated synthetic data, a paradigm we term Real-Synthetic Mix-Training (RSMT).

By Na Li, Boyu Kuang, Hongsheng Hu, Liquan Chen, Hyoungshick Kim, Yansong Gao, Anmin Fu

diffusion safety

arXiv AI

1d ago

SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling

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.

By Shixuan Sun, Siyuan Liang, Jianjie Huang, Jingzhi Li, Xiaochun Cao

llms rag multimodal safety

arXiv Machine Learning

Jun 18

RUB: Evaluating Residual Knowledge in Unlearned Models

arXiv:2504. 14798v2 Announce Type: replace Abstract: Machine Unlearning (MUL) has emerged as a key mechanism for privacy protection and content regulation, yet current techniques often fail to guarantee the complete removal of sensitive information.

By Hao Xuan, Xingyu Li

diffusion benchmarks safety

Related stories

Beyond Visual Forensics: Auditing Multimodal Robustness for Synthetic Medical Image Detection

Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection

Reducing information dependency does not cause training data privacy. Adversarially non-robust features do

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training

SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling

RUB: Evaluating Residual Knowledge in Unlearned Models