Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cao, Xiangkui, Zhang, Jie, Kan, Meina, Shan, Shiguang, Chen, Xilin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.12598