Journal article · 2026 · Open access
TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification
IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15 · Published 11 November 2026 · DOI 10.1109/tpami.2026.3752300
In brief
“TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification” is a 2026 journal article by Yuyuan Li and 7 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Pattern Analysis and Machine Intelligence.
- Citations
- 0
- Authors
- 8
Abstract
While deep neural networks (DNNs) are being widely adopted, they are also increasingly exposed to model stealing risks, posing significant threats to intellectual property. Model fingerprinting, which utilizes intrinsic characteristics derived from the training process to authenticate models, has been proposed as a potential solution. An ideal fingerprint should satisfy robustness, uniqueness, and efficiency. However, existing methods often struggle to balance these three aspects simultaneously. To address this challenge, we propose TRUE, a twostage fingerprint generation and verification framework. In the fingerprint generation stage, we adopt adversarial examples as the fingerprint type and enhance their robustness through a minmax robust optimization strategy. In the fingerprint verification stage, we assign weights to the adversarial examples using a Boltzmann distribution to reflect their uniqueness, and further employ sampling based on these weights to reduce the number of queries and improve efficiency. Extensive experiments conducted on real-world datasets and across different model architectures demonstrate the superiority of the TRUE framework.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, Y., Feng, X., Pan, L., Zhang, L., Zhang, L., Chen, C., Li, L., & Yan, C. C. (2026). TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15. https://doi.org/10.1109/tpami.2026.3752300
MLA 9
Li, Yuyuan, et al. “TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–15. https://doi.org/10.1109/tpami.2026.3752300.
Chicago
Li, Yuyuan, Xiaohua Feng, Le Pan, Li Zhang, Li Zhang, Chaochao Chen, Liang Li, and Chenggang Clarence Yan. 2026. “TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–15. https://doi.org/10.1109/tpami.2026.3752300.
Harvard
Li, Y. et al. (2026) ‘TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–15. doi:10.1109/tpami.2026.3752300.
IEEE
Y. Li et al., “TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–15, 2026, doi: 10.1109/tpami.2026.3752300.
BibTeX
@article{li2026true,
title = {{TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification}},
author = {Li, Yuyuan and Feng, Xiaohua and Pan, Le and Zhang, Li and Zhang, Li and Chen, Chaochao and Li, Liang and Yan, Chenggang Clarence},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {PP},
pages = {1--15},
doi = {10.1109/tpami.2026.3752300},
url = {https://doi.org/10.1109/tpami.2026.3752300}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- model fingerprinting
- model theft
- adversarial examples
- fingerprint verification
- query efficiency
- intellectual property protection
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Li, Y., Feng, X., Pan, L., Zhang, L., Zhang, L., Chen, C., Li, L., & Yan, C. C. (2026). TRUE: Towards Robust, Unique, and Efficient Model Fingerprint Generation and Verification. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15. https://doi.org/10.1109/tpami.2026.3752300
How many times has this paper been cited?
0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE Transactions on Pattern Analysis and Machine Intelligence: sign in and open the full text from this page.
Who wrote this paper?
Yuyuan Li, Xiaohua Feng, Le Pan, Li Zhang, Li Zhang, Chaochao Chen, Liang Li, Chenggang Clarence Yan.
What is the DOI of this paper?
10.1109/tpami.2026.3752300, permanently at https://doi.org/10.1109/tpami.2026.3752300. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.