Answer It or Not? Towards Prompt-Adapted Adversarial Images on Vision Language Models

cs.CV, cs.AI

Submitted: 2026-10-12

Updated: 2026-10-12

Comments: 20 pages, 7 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
• Explaining and Harnessing Adversarial Examples
• Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models
• Intriguing properties of neural networks
• OPT: Open Pre-trained Transformer Language Models
• BERTScore: Evaluating Text Generation with BERT
• Visual Adversarial Attack on Vision-Language Models for Autonomous Driving

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models