View in EDS

Secure yet fragile: adversarial vulnerabilities of federated vision-language models in medical AI.

Saved in:
Bibliographic Details
Title: Secure yet fragile: adversarial vulnerabilities of federated vision-language models in medical AI.
Authors: Fime AA; Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA., Samiha TZ; Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh., Hossain MZ; Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA., Zaman S; Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA., Shibli AM; Athlete Den, Westbury, 11590, USA., Shahid AR; Computer Science, Southern Illinois University, Carbondale, IL, 62901, USA., Ni Z; Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA., Imteaj A; Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA. aimteaj@fau.edu.
Source: Scientific reports [Sci Rep] 2026 Apr 16; Vol. 16 (1). Date of Electronic Publication: 2026 Apr 16.
Publication Type: Journal Article
Journal Info: Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:2045-2322
DOI:10.1038/s41598-026-48102-4