Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming

作者：Baoshun Tong, Haoran He, Ling Pan, Yang Liu, Liang Lin · 单位：School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China, The Hong Kong University of Science and Technology, Hong Kong · 会议/期刊：arXiv · 日期：2026-04-07 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Robustness / Attack