Year: 2026
Type: conference-paper
Abstract: 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 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 safetyenhancing 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 overdefense issue.We then introduce a mixed demonstration strategy as a trade-off solution for balancing security and performance under few-shot demonstration budget constraints 1 .
Authors: Zhiyu Xue, Reza Abbasi-Asl, Ramtin Pedarsani
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: National Science Foundation
OpenAlex ID: W7140093486