Fime, A. A., Samiha, T. Z., Hossain, M. Z., Zaman, S., Shibli, A. M., Shahid, A. R., Ni, Z., Imteaj, A. (2026). Secure yet fragile: adversarial vulnerabilities of federated vision–language models in medical AI. Scientific Reports. https://doi.org/10.1038/s41598-026-48102-4