Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Ruixin, Mendes, Ethan, Wang, Arthur, Hays, James, Das, Sauvik, Xu, Wei, Ritter, Alan
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.05023