Awesome Robotics Manipulation · full_paper

When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models

arXiv · 2025-11-20 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Robustness / Attack

VLA安全机器人学习
新标签打开 AlphaXiv新标签打开 Paper
When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）