[2603.18545] CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.18545 (cs) [Submitted on 19 Mar 2026 (v1), last revised 3 Apr 2026 (this version, v2)] Title:CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models Authors:Xiang Chen, Fangfang Yang, Chunlei Meng, Yuxian Dong, Ang Li, Yiwei Wei, Jiahuan Long, Jiujiang Guo, Chengyin Hu View a PDF of the paper titled CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models, by Xiang Chen and 8 other authors View PDF HTML (experimental) Abstract: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. To address this gap, we propose CoDA, a chain-of-distribution framework that constructs clinically plausible pipeline shifts by composing acquisition-like shading, reconstruction and display remapping, and delivery and export degradations. Under masked structural-similarity constraints, CoDA jointly optimizes stage compositions and parameters to induce failures while preserving visual plausibility...