EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Black-Box Model Copyright Verification Based on Adaptive Boundary Fingerprints

Xiaorui Yu, Zhaozhong Guo, Tianyi Zhang

Electronics · 13.07.2026 · 15 (14) · 3063

DOI: 10.3390/electronics15143063 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 13.07.2026. Verfasst von Xiaorui Yu und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing–Tianjin–Hebei Natural Science Foundation Cooperation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep-learning models are increasingly deployed in image recognition and intelligent decision-making, making model copyright verification important for protecting valuable digital assets. Existing structure- or parameter-based comparison methods are difficult to apply when only black-box access to a target model is available, and ordinary test samples often fail to reveal decision-boundary differences. This paper proposes a black-box copyright verification method based on adaptive boundary fingerprints. The method generates candidate boundary samples using the Fast Gradient Sign Method (FGSM), selects fingerprints under source correctness, margin, class balance, and diversity constraints, and measures source–target behavioral similarity by fusing label consistency, probability-distribution similarity, and boundary transition consistency. A decision threshold is then calibrated from the background distribution of independent models. Experiments on CIFAR-100 and Tiny-ImageNet show that independent models remain below calibrated thresholds, while most derived models obtain higher scores. On CIFAR-100, the method achieves a 91.7% detection rate and a 0.0% false-positive rate, with Area Under the Receiver Operating Characteristic Curve (AUROC) and Area Under the Precision-Recall Curve (AUPR) of 0.9750 and 0.9643, respectively. These results indicate that adaptive boundary fingerprints provide effective evidence for black-box model copyright verification.

Förderung

  • Beijing–Tianjin–Hebei Natural Science Foundation Cooperation Project

Zitieren

APA

Yu, X., Guo, Z., & Zhang, T. (2026). Black-Box Model Copyright Verification Based on Adaptive Boundary Fingerprints. Electronics, 15(14), 3063. https://doi.org/10.3390/electronics15143063

Vancouver

Yu X, Guo Z, Zhang T. Black-Box Model Copyright Verification Based on Adaptive Boundary Fingerprints. Electronics. 2026;15(14):3063. doi:10.3390/electronics15143063

BibTeX
@article{Yu2026,
  author = {Yu, Xiaorui and Guo, Zhaozhong and Zhang, Tianyi},
  title = {Black-Box Model Copyright Verification Based on Adaptive Boundary Fingerprints},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {14},
  pages = {3063},
  doi = {10.3390/electronics15143063}
}
Kostenlos starten →