Model Synthesis for Zero-Shot Model Attribution

doi:10.1109/TMM.2025.3607778

CSpace

	Model Synthesis for Zero-Shot Model Attribution
	Yang, Tianyun 1,2; Wang, Danding 1,2; Cao, Juan 1,2; Xu, Chang 3
	2025
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	27 页码:8967-8980
摘要	Nowadays, generative models are shaping various fields such as art, design, and human-computer interaction, yet they are accompanied by copyright infringement and content management challenges. In response, existing research seeks to identify the unique fingerprints on the images they generate, which can be leveraged to attribute the generated images to their source models. However, existing methods are restricted to identifying models within a static set included in classifier training, incapable of adapting dynamically to newly emerging unseen models. To bridge this gap, this paper aims to develop a generalized model fingerprint extractor capable of zero-shot attribution that effectively attributes unseen models without exposure during training. Central to our method is a model synthesis technique, which generates numerous synthetic models that mimic the fingerprint patterns of real-world generative models. The design of the synthesis technique is motivated by observations on how the basic generative model's architecture building blocks and parameters influence fingerprint patterns, and it is validated through designed metrics to examine synthetic models' fidelity. Our experiments demonstrate that the fingerprint extractor, trained solely on synthetic models, achieves impressive zero-shot generalization on a wide range of real-world generative models, improving model identification and verification accuracy on unseen models by over 40% and 15%, respectively, compared to existing approaches.
关键词	Fingerprint recognition Adaptation models Training Data models Analytical models Computational modeling Convolution Accuracy Training data Synthetic data Model fingerprint model attribution model synthesis zero-shot adaptation
DOI	10.1109/TMM.2025.3607778
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:001652357700001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42886
专题	中国科学院计算技术研究所
通讯作者	Cao, Juan
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Univ Sydney, Fac Engn, Sch Comp Sci, Sydney, NSW 2050, Australia
推荐引用方式 GB/T 7714	Yang, Tianyun,Wang, Danding,Cao, Juan,et al. Model Synthesis for Zero-Shot Model Attribution[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2025,27:8967-8980.
APA	Yang, Tianyun,Wang, Danding,Cao, Juan,&Xu, Chang.(2025).Model Synthesis for Zero-Shot Model Attribution.IEEE TRANSACTIONS ON MULTIMEDIA,27,8967-8980.
MLA	Yang, Tianyun,et al."Model Synthesis for Zero-Shot Model Attribution".IEEE TRANSACTIONS ON MULTIMEDIA 27(2025):8967-8980.