Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Zhiyu, Abbasi-Asl, Reza, Pedarsani, Ramtin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918437122473984
author Xue, Zhiyu
Abbasi-Asl, Reza
Pedarsani, Ramtin
author_facet Xue, Zhiyu
Abbasi-Asl, Reza
Pedarsani, Ramtin
contents Generative medical vision-language models~(Med-VLMs) are primarily designed to generate complex textual information~(e.g., diagnostic reports) from multimodal inputs including vision modality~(e.g., medical images) and language modality~(e.g., clinical queries). However, their security vulnerabilities remain underexplored. Med-VLMs should be capable of rejecting harmful queries, such as \textit{Provide detailed instructions for using this CT scan for insurance fraud}. At the same time, addressing security concerns introduces the risk of over-defense, where safety-enhancing mechanisms may degrade general performance, causing Med-VLMs to reject benign clinical queries. In this paper, we propose a novel inference-time defense strategy to mitigate harmful queries, enabling defense against visual and textual jailbreak attacks. Using diverse medical imaging datasets collected from nine modalities, we demonstrate that our defense strategy based on synthetic clinical demonstrations enhances model safety without significantly compromising performance. Additionally, we find that increasing the demonstration budget alleviates the over-defense issue. We then introduce a mixed demonstration strategy as a trade-off solution for balancing security and performance under few-shot demonstration budget constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09067
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
Xue, Zhiyu
Abbasi-Asl, Reza
Pedarsani, Ramtin
Computer Vision and Pattern Recognition
Artificial Intelligence
Generative medical vision-language models~(Med-VLMs) are primarily designed to generate complex textual information~(e.g., diagnostic reports) from multimodal inputs including vision modality~(e.g., medical images) and language modality~(e.g., clinical queries). However, their security vulnerabilities remain underexplored. Med-VLMs should be capable of rejecting harmful queries, such as \textit{Provide detailed instructions for using this CT scan for insurance fraud}. At the same time, addressing security concerns introduces the risk of over-defense, where safety-enhancing mechanisms may degrade general performance, causing Med-VLMs to reject benign clinical queries. In this paper, we propose a novel inference-time defense strategy to mitigate harmful queries, enabling defense against visual and textual jailbreak attacks. Using diverse medical imaging datasets collected from nine modalities, we demonstrate that our defense strategy based on synthetic clinical demonstrations enhances model safety without significantly compromising performance. Additionally, we find that increasing the demonstration budget alleviates the over-defense issue. We then introduce a mixed demonstration strategy as a trade-off solution for balancing security and performance under few-shot demonstration budget constraints.
title Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.09067