EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Open-Source Graph Dataset Infringement Verification Method via Class-Expansion Backdoor Watermark

Zuocheng Yu, Ming Xu, Xiaogang Xing, Yuanhao Lin, Yuwen Shu, Xiaohan Qi

Future Internet · 13.05.2026 · 18 (5) · 257

DOI: 10.3390/fi18050257 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 13.05.2026. Verfasst von Zuocheng Yu und 5 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of the Internet, open-source graph datasets are increasingly shared and reused in intelligent networked services, making robust infringement verification increasingly important. Backdoor-based watermarking for graph neural networks (GNNs) can be used to check whether a suspicious model has been trained on protected data without authorization. However, existing dataset infringement verification methods have limited applicability and are mainly designed for private datasets. Directly applying them to open-source datasets would cause models trained by legitimate users to learn backdoor behavior, which would expose them to security risks. In this paper, we propose a new infringement verification method for open-source graph datasets, which reduces backdoor-related security risks in models trained by legitimate users. The core idea is to introduce an additional expansion-class and re-label watermarked samples as belonging to this class. This design completely separates the learning of watermark patterns from the original feature-label mappings during training. As a result, only trigger-bearing samples are directly involved in infringement verification, which helps prevent watermark patterns from being associated with existing classes in the original task. The proposed method provides a practical solution for trustworthy graph data sharing and infringement verification in Internet environments. Extensive experiments on benchmark datasets demonstrate that the proposed method achieves a high verification success rate while largely preserving the model’s clean accuracy.

Zitieren

APA

Yu, Z., Xu, M., Xing, X., Lin, Y., Shu, Y., & Qi, X. (2026). An Open-Source Graph Dataset Infringement Verification Method via Class-Expansion Backdoor Watermark. Future Internet, 18(5), 257. https://doi.org/10.3390/fi18050257

Vancouver

Yu Z, Xu M, Xing X, Lin Y, Shu Y, Qi X. An Open-Source Graph Dataset Infringement Verification Method via Class-Expansion Backdoor Watermark. Future Internet. 2026;18(5):257. doi:10.3390/fi18050257

BibTeX
@article{Yu2026,
  author = {Yu, Zuocheng and Xu, Ming and Xing, Xiaogang and Lin, Yuanhao and Shu, Yuwen and Qi, Xiaohan},
  title = {An Open-Source Graph Dataset Infringement Verification Method via Class-Expansion Backdoor Watermark},
  journal = {Future Internet},
  year = {2026},
  volume = {18},
  number = {5},
  pages = {257},
  doi = {10.3390/fi18050257}
}
Kostenlos starten →