AI RESEARCH
When Minor Edits Matter: LLM-Driven Prompt Attack for Medical VLM Robustness in Ultrasound
arXiv CS.CV
•
ArXi:2603.21047v1 Announce Type: new Ultrasound is widely used in clinical practice due to its portability, cost-effectiveness, safety, and real-time imaging capabilities. However, image acquisition and interpretation remain highly operator dependent, motivating the development of robust AI-assisted analysis methods. Vision-language models (VLMs) have recently nstrated strong multimodal reasoning capabilities and competitive performance in medical image analysis, including ultrasound. However, emerging evidence highlights significant concerns about their trustworthiness.