Progressive Open Space Expansion for Open-Set Model Attribution

Despite the remarkable progress in generative technology, the Janus-faced issues of intellectual property protection and malicious content supervision have arisen. Efforts have been paid to manage synthetic images by attributing them to a set of potential source models. However, the closed-set class...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 15856 - 15865
Main Authors Yang, Tianyun, Wang, Danding, Tang, Fan, Zhao, Xinying, Cao, Juan, Tang, Sheng
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2023
Subjects
accountability
Computational modeling
Computer architecture
Computer vision
ethics in vision
fairness
Focusing
Image recognition
Intellectual property
privacy
Semantics
Transparency
Online AccessGet full text

Cover

More Information
Summary:Despite the remarkable progress in generative technology, the Janus-faced issues of intellectual property protection and malicious content supervision have arisen. Efforts have been paid to manage synthetic images by attributing them to a set of potential source models. However, the closed-set classification setting limits the application in real-world scenarios for handling contents generated by arbitrary models. In this study, we focus on a challenging task, namely Open-Set Model Attribution (OSMA), to simultaneously attribute images to known models and identify those from unknown ones. Compared to existing openset recognition (OSR) tasks focusing on semantic novelty, OSMA is more challenging as the distinction between images from known and unknown models may only lie in visually imperceptible traces. To this end, we propose a Progressive Open Space Expansion (POSE) solution, which simulates open-set samples that maintain the same semantics as closed-set samples but embedded with different imperceptible traces. Guided by a diversity constraint, the open space is simulated progressively by a set of lightweight augmentation models. We consider three real-world scenarios and construct an OSMA benchmark dataset, including unknown models trained with different random seeds, architectures, and datasets from known ones. Extensive experiments on the dataset demonstrate POSE is superior to both existing model attribution methods and off-the-shelf OSR methods. Github: https://github.com/ICTMCG/POSE
ISSN:2575-7075
DOI:10.1109/CVPR52729.2023.01522