DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Zonghuan, Li, Jiayu, Zhao, Yunhan, Zheng, Xiang, Ma, Xingjun, Jiang, Yu-Gang
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.10932