Article

OCR-Mediated Modality Dominance in Vision-Language Models: Implications for Radiology AI Trustworthiness

2026-02-24

Abstract excerpt

1. <h4>Background</h4> Vision-language models (VLMs) are increasingly proposed for radiologic decision support, yet the security implications of deploying general-domain, OCR-capable models in diagnostic workflows remain poorly characterized. When image-embedded text is not treated as untrusted input, the visual channel becomes vulnerable to adversarial manipulation through OCR-readable overlays. <h4>Methods</h4>...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 8bfbb01a-8cc6-5cc6-8257-a9b3cf95b628
DOI: 10.64898/2026.02.22.26346828

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

OCR-Mediated Modality Dominance in Vision-Language Models: Implications for Radiology AI TrustworthinessDOI 10.64898/2026.02.22.26346828Read

Image-embedded prompt injection vulnerability of vision-language models in dental radiology: a cross-vendor attack–defense evaluationSemantic proximity Read

Prompt injection attacks on vision-language models for surgical decision supportSemantic proximity Read

More Harm than Help? Evaluating the Capabilities of Vision-Language Models in Neurological Image AnalysisSemantic proximity Read

Large Language Models Are Highly Vulnerable to Adversarial Hallucination Attacks in Clinical Decision Support: A Multi-Model Assurance AnalysisSemantic proximity Read

Vision and Language Models for Classifying Maxillary Sinus Disease on Cone-Beam Computed Tomography: A Transparent Multimodal BenchmarkSemantic proximity Read

Benchmarking Multimodal Large Language Models for Forensic Science and Medicine: A Comprehensive Dataset and Evaluation FrameworkSemantic proximity Read

A Clinically-Informed Framework for Evaluating Vision-Language Models in Radiology Report Generation: Taxonomy of Errors and Risk-Aware MetricSemantic proximity Read

Board-Level Performance of Leading Open-Weight Vision-Language Models on the Japanese Diagnostic Radiology Board Examination: Reasoning, Image-Input, and Language EffectsSemantic proximity Read

Language-dependent diagnostic safety of medical AI systems: a cross-lingual benchmarking and prospective clinical studySemantic proximity Read

A multi-model study of diagnostic faithfulness in AI-generated histopathology imagesSemantic proximity Read

SlideFlame: A data-efficient vision-language model for anatomically grounded pathology reportingSemantic proximity Read

Invisible Text Injection: The Trojan Horse of AI-Assisted Medical Peer ReviewSemantic proximity Read