Metraipolis › archive › dc_bd74f769fa5f

A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification — arXiv:2609.04772

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04772
License (as archived)
CC0-1.0
Archived
2026-10-16T22:58:10.034Z
SHA-256 of the archived text
f4f9a5d4313ac73b0f5027fe1f2f06a8f6f2281086bf87ef99a92c235aa186d4
Stable URL of this page
https://metraipolis.com/documento/dc_bd74f769fa5f

How to cite

A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification — arXiv:2609.04772 — arXiv (en), https://arxiv.org/abs/2609.04772 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd74f769fa5f (Metraipolis archive dc_bd74f769fa5f, sha256 f4f9a5d4313ac73b0f5027fe1f2f06a8f6f2281086bf87ef99a92c235aa186d4)
BibTeX
@misc{dcbd74f769fa5f,
  title = {A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification — arXiv:2609.04772},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04772},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd74f769fa5f; sha256 f4f9a5d4313ac73b0f5027fe1f2f06a8f6f2281086bf87ef99a92c235aa186d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04772. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The high training cost of Graph Neural Networks (GNNs) has raised growing concerns regarding model ownership infringement, such as model stealing and unauthorized misuse. To verify model ownership and prevent significant economic losses, two groups of GNN Ownership Verification (OV) methods have been proposed: watermark-based methods and fingerprint-based methods. However, these methods typically face three limitations: (1) the performance degradation of protected models caused by out-of-distribution (OOD) watermark graphs with respect to the training set; (2) the unrealistic assumption that surrogate models have been trained on a watermark-containing training set; and (3) over-reliance on specific output levels for fingerprint extraction. In this paper, we propose a Robust watErMArk-based fingeRprint frameworK for GNNs, named REMARK. REMARK first generates carefully crafted in-distribution watermark graphs that maximize output differences between GNN models, thus mitigating OOD-induced performance degradation. REMARK then extracts robust fingerprints from these output differences to verify GNN ownership, thereby removing the assumptions that surrogate models must be trained on a watermark-containing dataset or expose specific output levels. Extensive experiments across widely used real-world datasets and GNN architectures demonstrate that REMARK achieves state-of-the-art OV accuracy and robustness while preserving the utility of protected models.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.04772 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T22:31:32.187Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).