Medical MLLM Is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models | OpenReview

Medical MLLM Is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models

Open Webpage

Xijie Huang, Xinyuan Wang, Hantao Zhang, Yinghao Zhu, Jiawen Xi, Jingkun An, Hao Wang, Hao Liang, Chengwei Pan

Published: 2025, Last Modified: 28 Feb 2026AAAI 2025EveryoneRevisionsBibTeXCC BY-SA 4.0

Loading