Back to search

Article

Prompt injection attacks on vision-language models for surgical decision support

2025-07-23

Abstract excerpt

<h4>Importance</h4> Artificial Intelligence-driven analysis of laparoscopic video holds potential to increase the safety and precision of minimally invasive surgery. Vision-language models are particularly promising for video-based surgical decision support due to their capabilities to comprehend complex temporospatial (video) data. However, the same multimodal interfaces that enable such capabilities also introd...

Topics

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

Identifiers and source

Literature Corpus work
c4f2a3da-1e58-5ab3-9ee9-a4e4bea93f85
DOI
10.1101/2025.07.16.25331645
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Prompt injection attacks on vision-language models for surgical decision supportDOI 10.1101/2025.07.16.25331645
OCR-Mediated Modality Dominance in Vision-Language Models: Implications for Radiology AI TrustworthinessSemantic proximity
Large Language Models Are Highly Vulnerable to Adversarial Hallucination Attacks in Clinical Decision Support: A Multi-Model Assurance AnalysisSemantic proximity
Image-embedded prompt injection vulnerability of vision-language models in dental radiology: a cross-vendor attack–defense evaluationSemantic proximity
Language-dependent diagnostic safety of medical AI systems: a cross-lingual benchmarking and prospective clinical studySemantic proximity
Red-Teaming Medical AI: Systematic Adversarial Evaluation of LLM Safety Guardrails in Clinical ContextsSemantic proximity
More Harm than Help? Evaluating the Capabilities of Vision-Language Models in Neurological Image AnalysisSemantic proximity
Assessment of ChatGPT in the preclinical management of ophthalmological emergencies – an analysis of ten fictional case vignettesSemantic proximity
An Evaluation of the Safety of ChatGPT with Malicious Prompt InjectionSemantic proximity
Medical Lie Detector (MLD): A Hybrid System for Validating AI Clinical Compiled SummariesSemantic proximity
Automated Task-Specific vs General-Purpose Artificial Intelligence for Detecting Subtle Intraoperative Warning Signs During Cataract Surgery: A Multicenter Diagnostic StudySemantic proximity
A Clinically-Informed Framework for Evaluating Vision-Language Models in Radiology Report Generation: Taxonomy of Errors and Risk-Aware MetricSemantic proximity
Invisible Text Injection: The Trojan Horse of AI-Assisted Medical Peer ReviewSemantic proximity
Select a neighboring publication to make it the new centre.