EUVIMEDEUVIMED entdecken
Crossref

Rotation, Scale, and Translation Resilient Black-Box Fingerprinting for Intellectual Property Protection of EaaS Models

Hongjie Zhang, Zhiqi Zhao, Hanzhou Wu, Zhihua Xia, Athanasios V. Vasilakos

IEEE Transactions on Dependable and Secure Computing · 2026-07 · 23 (4) · 8079-8092

DOI: 10.1109/tdsc.2026.3680342 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Dependable and Secure Computing, 2026-07. Verfasst von Hongjie Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Feature embedding has become a cornerstone technology for processing high-dimensional and complex data, which results in that Embedding as a Service (EaaS) models have been widely deployed in the cloud. To protect the intellectual property of EaaS models, existing methods apply digital watermarking to inject specific backdoor triggers into EaaS models by modifying training samples or network parameters. However, these methods inevitably produce detectable patterns through semantic analysis and exhibit susceptibility to geometric transformations including rotation, scaling, and translation (RST). To address this problem, we propose a novel fingerprinting framework called POSTER for EaaS models, rather than merely refining existing watermarking techniques. Different from watermarking, the proposed POSTER establishes EaaS model ownership through geometric analysis of embedding space’s topological structure, rather than relying on the modified training samples or triggers. The key innovation lies in modeling the victim and suspicious embeddings as point clouds, allowing us to perform robust spatial alignment and similarity measurement, which inherently resists RST attacks. Experiments evaluated on visual and textual embedding tasks verify the superiority and applicability. This work reveals inherent characteristics of EaaS models and provides a promising solution for ownership verification of EaaS models under black-box scenarios.

Zitieren

APA

Zhang, H., Zhao, Z., Wu, H., Xia, Z., & Vasilakos, A. V. (2026). Rotation, Scale, and Translation Resilient Black-Box Fingerprinting for Intellectual Property Protection of EaaS Models. IEEE Transactions on Dependable and Secure Computing, 23(4), 8079-8092. https://doi.org/10.1109/tdsc.2026.3680342

Vancouver

Zhang H, Zhao Z, Wu H, Xia Z, Vasilakos AV. Rotation, Scale, and Translation Resilient Black-Box Fingerprinting for Intellectual Property Protection of EaaS Models. IEEE Transactions on Dependable and Secure Computing. 2026;23(4):8079-8092. doi:10.1109/tdsc.2026.3680342

BibTeX
@article{Zhang2026,
  author = {Zhang, Hongjie and Zhao, Zhiqi and Wu, Hanzhou and Xia, Zhihua and Vasilakos, Athanasios V.},
  title = {Rotation, Scale, and Translation Resilient Black-Box Fingerprinting for Intellectual Property Protection of EaaS Models},
  journal = {IEEE Transactions on Dependable and Secure Computing},
  year = {2026},
  volume = {23},
  number = {4},
  pages = {8079--8092},
  doi = {10.1109/tdsc.2026.3680342}
}
Kostenlos starten →