English(EN) GENIE: Watermarking Graph Neural Networks for Link Prediction

GENIE水印方案保护用于链接预测的GNN

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

研究人员开发了GENIE，这是一种新颖的水印方案，旨在保护用于链接预测的图神经网络（GNN）模型。与以往专注于节点或图分类的方法不同，GENIE解决了在链接预测任务中保护GNN的特定挑战。该系统采用独特的触发集和秘密水印向量，并结合动态水印阈值（DWT）以确保高验证准确性以及对各种移除技术和攻击的鲁棒性。 AI

影响为保护基于图的机器学习模型的知识产权提供了一种新方法。

排序理由该集群包含一篇详细介绍GNN水印新方法的学术论文。[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 →

本文如何被排名

Signal score: 24 / 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水印新方法的学术论文。[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, safety; 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) · Venkata Sai Pranav Bachina, Aaryan Ajay Sharma, Ankit Gangwal, Charu Sharma · 2026-09-02 04:00

GENIE: 为链接预测的水印图神经网络

arXiv:2406.04805v4 Announce Type: replace-cross Abstract: The rapid adoption, usefulness, and resource-intensive training of Graph Neural Network (GNN) models have made them an invaluable intellectual property in graph-based machine learning. However, their wide-spread adoption a…

本文如何被排名

报道来源 [1]

GENIE: 为链接预测的水印图神经网络

相关实体

相关话题