Medical VLP Model Is Vulnerable: Toward Multimodal Adversarial Attack on Large Medical Vision-Language Models - researchr publication

researchr

You are not signed in
Sign in
Sign up

Zimu Lu, Ning Xu 0003, Hongshuo Tian, Lanjun Wang, An-An Liu. Medical VLP Model Is Vulnerable: Toward Multimodal Adversarial Attack on Large Medical Vision-Language Models. IEEE Trans. Circuits Syst. Video Techn., 36(2):2478-2491, February 2026. [doi]

Abstract is missing.

runs on WebDSL