Author name: Xiyang Wu, Guangyao Shi, Qingzi Wang, Zongxia Li, Amrit Singh Bedi, Dinesh Manocha

arXiv:2603.24935v2 Announce Type: replace
Abstract: Vision-language-action (VLA) models enable robots to follow natural-language instructions grounded in visual observations, but the instruction channel also introduces a critical vulnerability: small …

arXiv:2603.24935v1 Announce Type: new
Abstract: Vision-language-action (VLA) models enable robots to follow natural-language instructions grounded in visual observations, but the instruction channel also introduces a critical vulnerability: small text…