CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion

Published in CVPR 2024, 2024

In this paper, we crafted a visualizable copyright authentication mechanism by modeling and analyzing the conceptual difference between fine-tuned and pretrained diffusion models theoretically. This work has been packaged into an open-source project called** ** Revelio :


Revelio: Digital Copyright Authentication for Diffusion Models Mar. 2024 — Present

Homepage :https://github.com/Nicholas0228/Revelio

Recommended citation: Wu X, Hua Y, Liang C, et al. (2024). "CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion." CVPR 2024.
Download Paper