Loading
Life sciences · Preprint
arXiv · September 4, 2026
Posted before peer review. The findings may change or fail to hold.
This is an unrefereed preprint proposing REMARK, a framework for verifying ownership of Graph Neural Networks using watermarking and fingerprinting. The work addresses technical vulnerabilities in prior GNN ownership verification methods and reports achieving state-of-the-art accuracy and robustness in experimental validation, but the abstract provides no quantitative results, comparison metrics, or peer-reviewed publication status.
Preprint. Intervention: REMARK framework: in-distribution watermark graph generation followed by fingerprint extraction from output differences.
REMARK generates in-distribution watermark graphs to mitigate performance degradation caused by out-of-distribution watermark examples Framework removes requirement that surrogate models be trained on watermark-containing datasets Reported to achieve state-of-the-art OV accuracy and robustness while preserving protected model utility
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an unrefereed arXiv preprint describing a computer science methodology for GNN model ownership verification; it has not undergone peer review and reports no clinical or human trial data.
As stated by the source record.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
What is missing. This record has no reported figures. That is a gap in the analysis, not a judgement about the study.
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.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.