Synthetic clinical demonstrations at inference time improve safety of Med-VLMs against visual and textual jailbreaks while preserving general performance on medical tasks.
Jailbreaking black box large language models in twenty queries
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
Synthetic clinical demonstrations at inference time improve safety of Med-VLMs against visual and textual jailbreaks while preserving general performance on medical tasks.