Awesome Robotics Manipulation · full_paper

Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects

arXiv · 2025-10-10 · 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新标签打开 Code
Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects figure
AlphaXiv 中文论文页面（可滚动查看）