MAID: Model Attribution via Inverse Diffusion

The surge in AI-generated images, blending authentic and synthetic content, raises security concerns and complicates model attribution, especially with limited transparency. Existing methods either struggle to attribute across multiple frameworks or rely on additional conditions, such as textual des...

Full description

Bibliographic Details

Published in:	Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 1 - 5
Main Authors:	Zhu, Luyu, Ye, Kai, Yao, Jiayu, Li, Chenxi, Zhao, Luwen, Cao, Yuxin, Wang, Derui, Hao, Jie
Format:	Conference Proceeding
Language:	English
Published:	IEEE 06.04.2025
Subjects:	Autoencoders Deepfake Diffusion Model Diffusion models Diffusion processes Feature extraction Glass box Limiting Model Attribution Noise reduction Security Speech processing Surges
ISSN:	2379-190X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!