AI RESEARCH
Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving: A Cross-Architecture Analysis
arXiv CS.LG
•
ArXi:2604.27414v1 Announce Type: cross Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, ing interpretable decision-making, yet their robustness to physical adversarial attacks, especially whether such attacks transfer across different VLM architectures, is not well understood and poses a practical risk when attackers do not know which model a vehicle uses.