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

• URL: http://arxiv.org/abs/2603.18545v1
• Date: Thu, 19 Mar 2026 07:00:44 GMT
• Title: CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models
• Abstract summary: We propose a chain-of-distribution framework that constructs clinically plausible pipeline shifts by acquisition-like shading, reconstruction and display remapping, and delivery and export degradations.<n>Across brain MRI, chest X-ray, and abdominal CT, CoDA substantially degrades the zero-shot performance of CLIP-style MVLMs.<n>We also evaluate multimodal large language models (MLLMs) as technical-authenticity auditors of imaging realism and quality rather than pathology.
• Score: 14.039516906417724
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. Across brain MRI, chest X-ray, and abdominal CT, CoDA substantially degrades the zero-shot performance of CLIP-style MVLMs, with chained compositions consistently more damaging than any single stage. We also evaluate multimodal large language models (MLLMs) as technical-authenticity auditors of imaging realism and quality rather than pathology. Proprietary multimodal models show degraded auditing reliability and persistent high-confidence errors on CoDA-shifted samples, while the medical-specific MLLMs we test exhibit clear deficiencies in medical image quality auditing. Finally, we introduce a post-hoc repair strategy based on teacher-guided token-space adaptation with patch-level alignment, which improves accuracy on archived CoDA outputs. Overall, our findings characterize a clinically grounded threat surface for MVLM deployment and show that lightweight alignment improves robustness in deployment.

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• Masked and Predictive Self-Supervised Foundation Models for 3D Brain MRI [0.0]
  We investigate two major self-supervised pretraining paradigms for MRI-based disease detection.<n>We study the role of auxiliary objectives by introducing a novel spectral-domain reconstruction loss for MAE.<n>Our results highlight the importance of self-supervised objective design for medical foundation model pretraining.
  arXiv  Detail & Related papers  (2026-06-11T13:09:59Z)
• Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models [56.29123284262618]
  This work proposes leveraging the universal representation capabilities of visual foundation models to estimate inherent data uncertainty.<n>We analyze the feature diversity of the model's decoded representations and quantify their singular value energy to define the semantic perception scale for each class.<n>Based on this foundation, we design two uncertainty-driven application strategies: (1) the aleatoric uncertainty-aware data filtering mechanism to eliminate potentially noisy samples and enhance model learning quality; and (2) the dynamic uncertainty-aware optimization strategy that adaptively adjusts class-specific loss weights during training based on the semantic perception scale, combined with a label denoising mechanism to improve training stability
  arXiv  Detail & Related papers  (2026-04-13T03:59:54Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• CLEAR-Mamba:Towards Accurate, Adaptive and Trustworthy Multi-Sequence Ophthalmic Angiography Classification [18.95392587947337]
  Medical image classification is a core task in computer-aided diagnosis (CAD)<n>In ophthalmic practice, fluorescein fundus angiography (FFA) and indocyanine green angiography (ICGA) provide hemodynamic and lesion-structural information.<n>We propose CLEAR-Mamba, an enhanced framework built upon MedMamba with optimizations in both architecture and training strategy.
  arXiv  Detail & Related papers  (2026-01-28T13:40:10Z)
• Aligning Findings with Diagnosis: A Self-Consistent Reinforcement Learning Framework for Trustworthy Radiology Reporting [37.57009831483529]
  Multimodal Large Language Models (MLLMs) have shown strong potential for radiology report generation.<n>Our framework restructures generation into two distinct components: a think block for detailed findings and an answer block for structured disease labels.
  arXiv  Detail & Related papers  (2026-01-06T14:17:44Z)
• Cancer-Net PCa-MultiSeg: Multimodal Enhancement of Prostate Cancer Lesion Segmentation Using Synthetic Correlated Diffusion Imaging [55.62977326180104]
  Current deep learning approaches for prostate cancer lesion segmentation achieve limited performance.<n>We investigate synthetic correlated diffusion imaging (CDI$s$) as an enhancement to standard diffusion-based protocols.<n>Our results establish validated integration pathways for CDI$s$ as a practical drop-in enhancement for PCa lesion segmentation tasks.
  arXiv  Detail & Related papers  (2025-11-11T04:16:12Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• Prompt-Guided Patch UNet-VAE with Adversarial Supervision for Adrenal Gland Segmentation in Computed Tomography Medical Images [0.3437656066916039]
  Small abdominal organs, such as the adrenal glands in CT imaging, remains a persistent challenge due to severe class imbalance, poor spatial context, and limited annotated data.<n>We propose a unified framework that combines variational reconstruction, supervised segmentation, and adversarial patch-based feedback to address these limitations in a principled and scalable manner.<n>Our findings highlight the effectiveness of hybrid generative-discriminative training regimes for small-organ segmentation and provide new insights into balancing realism, diversity, and anatomical consistency in data-scarce scenarios.
  arXiv  Detail & Related papers  (2025-09-03T10:18:06Z)
• On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable? [0.9626666671366837]
  We introduce MediMeta-C, a corruption benchmark that applies several perturbations across multiple medical imaging datasets.<n>We propose RobustMedCLIP, a visual encoder adaptation of a pretrained MVLM that incorporates few-shot tuning to enhance resilience against corruptions.
  arXiv  Detail & Related papers  (2025-05-21T12:08:31Z)
• InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration [106.70903819362402]
  Diffusion priors have been used for blind face restoration (BFR) by fine-tuning diffusion models (DMs) on restoration datasets to recover low-quality images.<n>We propose InterLCM to leverage the latent consistency model (LCM) for its superior semantic consistency and efficiency.<n>InterLCM outperforms existing approaches in both synthetic and real-world datasets while also achieving faster inference speed.
  arXiv  Detail & Related papers  (2025-02-04T10:51:20Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.