Awesome Robotics Manipulation · full_paper

TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches

作者：Zhengxian Huang, Wenjun Zhu, Haoxuan Qiu, Xiaoyu Ji, Wenyuan Xu · 单位：Zhejiang University, Hangzhou, China Harbin Institute · 会议/期刊：arXiv · 日期：2026-03-24 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Robustness / Attack

视觉语言动作安全机器人学习
新标签打开 AlphaXiv新标签打开 Paper
TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches figure
AlphaXiv 中文论文页面（可滚动查看）