BOSC: A Backdoor-Based Framework for Open Set Synthetic Image Attribution

With the continuous progress of AI technology, new generative architectures continuously appear, thus driving the attention of researchers towards the development of synthetic image attribution methods capable of working in open-set scenarios. Existing approaches focus on extracting highly discrimin...

Full description

Bibliographic Details

Published in:	IEEE transactions on information forensics and security Vol. 20; pp. 8043 - 8058
Main Authors:	Wang, Jun, Tondi, Benedetta, Barni, Mauro
Format:	Journal Article
Language:	English
Published:	IEEE 2025
Subjects:	Analytical models Autoencoders backdoor injection Computer architecture deep learning for multimedia forensics Facial features Feature extraction Image forensics Image recognition open set recognition Prototypes Robustness Synthetic image attribution Training
ISSN:	1556-6013, 1556-6021
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!