Back

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

2025-07-23 surgery Title + abstract only
View on medRxiv
Show abstract

ImportanceArtificial 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 introduce new vulnerabilities to manipulations through embedded deceptive text or images (prompt inj...

Predicted journal destinations