BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Xueyang, Tie, Guiyao, Zhang, Guowen, Wang, Hechang, Zhou, Pan, Sun, Lichao
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence 68T07 I.2.6; I.2.9
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2505.16640