AI RESEARCH
CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models
arXiv CS.AI
•
ArXi:2603.18545v1 Announce Type: cross Medical vision--language models (MVLMs) are increasingly used as perceptual backbones in radiology pipelines and as the visual front end of multimodal assistants, yet their reliability under real clinical workflows remains underexplored. Prior robustness evaluations often assume clean, curated inputs or study isolated corruptions, overlooking routine acquisition, reconstruction, display, and delivery operations that preserve clinical readability while shifting image statistics.