Assessing the adversarial robustness of multimodal medical AI systems: insights into vulnerabilities and modality interactions

Assessing the adversarial robustness of multimodal medical AI systems: insights into vulnerabilities and modality interactions

The emergence of both task-specific single-modality models and general-purpose multimodal large models presents new opportunities, but also introduces challenges, particularly regarding adversarial attacks. In high-stakes domains like healthcare, these attacks can severely undermine model reliabilit...

Full description

Saved in:
Bibliographic Details
Main Authors: Ekaterina Mozhegova, Asad Masood Khattak, Adil Khan, Roman Garaev, Bader Rasheed, Muhammad Shahid Anwar
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Medicine
Subjects:
machine learning (ML)
adversarial attack
multimodal data fusion
classification
X-ray
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1606238/full
Tags: Add Tag
No Tags, Be the first to tag this record!
Login for hold and recall information

Internet

https://www.frontiersin.org/articles/10.3389/fmed.2025.1606238/full

Similar Items