Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies

作者：Siddharth Srikanth, Freddie Liang, Ya-Chuan Hsu, Varun Bhatt, Shihan Zhao, Henry Chen, Bryon Tjanaka, Minjune Hwang, Akanksha Saran, Daniel Seita, Aaquib Tabrez, Stefanos Nikolaidis misses can · 单位：Thomas Lord Department of Computer Science, University of Southern, California, Sony AI, Sibley School of Mechanical and Aerospace En, gineering, Cornell University. Equal advisement · 会议/期刊：arXiv · 日期：2026-03-12 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Robustness / Attack