Cover Image

Consistent but Dangerous: Per-Sample Safety Classification Reveals False Reliability in Medical Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sadanandan, Binesh, Behzadan, Vahid
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mechanistically Guided LoRA Improves Paraphrase Consistency in Medical Vision-Language Models
by: Sadanandan, Binesh, et al.
Published: (2026)

PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models
by: Sadanandan, Binesh, et al.
Published: (2026)

VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models
by: Sadanandan, Binesh, et al.
Published: (2025)

When Chain-of-Thought Backfires: Evaluating Prompt Sensitivity in Medical Language Models
by: Sadanandan, Binesh, et al.
Published: (2026)

Predictive Entropy Links Calibration and Paraphrase Sensitivity in Medical Vision-Language Models
by: Sadanandan, Binesh, et al.
Published: (2026)

Promise of Data-Driven Modeling and Decision Support for Precision Oncology and Theranostics
by: Sadanandan, Binesh, et al.
Published: (2025)

Comparative Study of Generative Models for Early Detection of Failures in Medical Devices
by: Sadanandan, Binesh, et al.
Published: (2025)

Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models
by: Liang, Xiao, et al.
Published: (2025)

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models
by: Meng, Yu, et al.
Published: (2025)

Leveraging Vision-Language Foundation Models to Reveal Hidden Image-Attribute Relationships in Medical Imaging
by: Kumar, Amar, et al.
Published: (2025)

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
by: Xue, Zhiyu, et al.
Published: (2025)

Test-Time Consistency in Vision Language Models
by: Chou, Shih-Han, et al.
Published: (2025)

ViDAS: Vision-based Danger Assessment and Scoring
by: Gupta, Pranav, et al.
Published: (2024)

6 Fingers, 1 Kidney: Natural Adversarial Medical Images Reveal Critical Weaknesses of Vision-Language Models
by: Mayer, Leon, et al.
Published: (2025)

Judge Like a Real Doctor: Dual Teacher Sample Consistency Framework for Semi-supervised Medical Image Classification
by: Qixiang, Zhang, et al.
Published: (2024)

Consistency-guided Prompt Learning for Vision-Language Models
by: Roy, Shuvendu, et al.
Published: (2023)

Unveiling the Tapestry of Consistency in Large Vision-Language Models
by: Zhang, Yuan, et al.
Published: (2024)

ReViP: Mitigating False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance
by: Li, Zhuohao, et al.
Published: (2026)

Intersectional Fairness in Vision-Language Models for Medical Image Disease Classification
by: Zhang, Yupeng, et al.
Published: (2025)

MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)
by: Chou, Shih-Han, et al.
Published: (2024)

Benchmarking Vision-Language Contrastive Methods for Medical Representation Learning
by: Roy, Shuvendu, et al.
Published: (2024)

Few-shot Adaptation of Medical Vision-Language Models
by: Shakeri, Fereshteh, et al.
Published: (2024)

Full Conformal Adaptation of Medical Vision-Language Models
by: Silva-Rodríguez, Julio, et al.
Published: (2025)

On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?
by: Imam, Raza, et al.
Published: (2025)

On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations
by: Vice, Jordan, et al.
Published: (2025)

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
by: Lee, Seongyun, et al.
Published: (2024)

Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models
by: Shi, Enyi, et al.
Published: (2026)

Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification
by: Ye, Yaoqin, et al.
Published: (2024)

MAFA: Managing False Negatives for Vision-Language Pre-training
by: Byun, Jaeseok, et al.
Published: (2023)

Using Vision Language Models for Safety Hazard Identification in Construction
by: Adil, Muhammad, et al.
Published: (2025)

Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification
by: Weng, Charles, et al.
Published: (2026)

Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation
by: Yang, Longzhen, et al.
Published: (2025)

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models
by: Zhang, Jie, et al.
Published: (2025)

Calibration-Aware Prompt Learning for Medical Vision-Language Models
by: Basu, Abhishek, et al.
Published: (2025)

Delving into Out-of-Distribution Detection with Medical Vision-Language Models
by: Ju, Lie, et al.
Published: (2025)

Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
by: Chen, Jiawei, et al.
Published: (2024)

Safety Alignment for Vision Language Models
by: Liu, Zhendong, et al.
Published: (2024)

Improved EATFormer: A Vision Transformer for Medical Image Classification
by: Shisu, Yulong, et al.
Published: (2024)

Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classification
by: Gallée, Luisa, et al.
Published: (2025)

False Promises in Medical Imaging AI? Assessing Validity of Outperformance Claims
by: Christodoulou, Evangelia, et al.
Published: (2025)