New REMARK framework enhances GNN ownership verification

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

研究人员开发了REMARK，一个用于验证图神经网络（GNN）所有权的新框架。该方法通过生成最小化性能下降的in-distribution水印图来解决现有水印和指纹技术的局限性。REMARK从输出差异中提取鲁棒的指纹，无需在包含水印的数据集上训练代理模型，也无需暴露特定的输出级别。实验表明，REMARK在GNN所有权验证方面实现了最先进的准确性和鲁棒性，同时保持了模型的效用。 AI

影响该框架有助于保护知识产权，防止未经授权使用成本高昂的GNN模型。

排序理由该集群包含一篇详细介绍GNN所有权验证新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

New REMARK framework enhances GNN ownership verification

本文如何被排名

Signal score: 27 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍GNN所有权验证新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Han Zhang, Yan Wang, Guanfeng Liu, Pengfei Ding, Huaxiong Wang, Kwok-Yan Lam · 2026-09-07 04:00

用于GNN所有权验证的基于水印的鲁棒指纹框架

arXiv:2609.04772v1 Announce Type: new Abstract: 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 lo…

本文如何被排名

报道来源 [1]

用于GNN所有权验证的基于水印的鲁棒指纹框架

相关实体

相关话题