← Publications
AAAI 2025Published

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

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

AAAI arXiv Code Citation
The 3MAD dataset spans medical imaging modalities and question types used to evaluate medical multimodal model safety.
The 3MAD dataset spans medical imaging modalities and question types used to evaluate medical multimodal model safety.

TL;DR

The 3MAD dataset and MCM optimization expose cross-modal safety weaknesses in medical multimodal language models.通过 3MAD 数据集与 MCM 优化，揭示医疗多模态大语言模型在图文错配及跨模态攻击下的安全薄弱点。

Citation

Download .bib
@article{huang2025medical,
  title = {Medical {MLLM} Is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models},
  author = {Huang, Xijie and Wang, Xinyuan and Zhang, Hantao and Zhu, Yinghao and Xi, Jiawen and An, Jingkun and Wang, Hao and Liang, Hao and Pan, Chengwei},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {39},
  number = {4},
  pages = {3797--3805},
  year = {2025},
  doi = {10.1609/aaai.v39i4.32396},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32396}
}