VSF-Med introduces an eight-dimension, judge-scored vulnerability score for medical VLMs and reports that all five tested models are most vulnerable to persistent attack effects, with Llama-3.2 showing the largest drop.
Corpa: Adversar- ial image generation for chest x-rays using concept vec- tor perturbations and generative models.arXiv preprint arXiv:2502.05214,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models
VSF-Med introduces an eight-dimension, judge-scored vulnerability score for medical VLMs and reports that all five tested models are most vulnerable to persistent attack effects, with Llama-3.2 showing the largest drop.