English(EN) GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearning

新的GraphToxin攻击可从GNN中重建已删除数据

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员开发了GraphToxin，一种能够从图神经网络（GNN）中重建整个未学习图的新型攻击。该方法超越了以往的成员推理攻击，不仅恢复了已删除的单个数据，还恢复了其邻居的敏感信息。GraphToxin利用曲率匹配模块进行细粒度引导，并在白盒和黑盒场景中都显示出有效性，突显了当前图解构验证标准的局限性。 AI

影响这项研究突显了当前图解构技术的重大漏洞，可能影响处理图数据的AI系统中的数据隐私和安全。

排序理由该集群包含一篇详细介绍针对图解构的新攻击方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 25 / 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针对图解构的新攻击方法的论文。[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.AI TIER_1 English(EN) · Ying Song, Balaji Palanisamy · 2026-10-01 04:00

GraphToxin：从图解构中重建完整的未学习图

arXiv:2511.10936v3 Announce Type: replace-cross Abstract: Graph unlearning (GU) has emerged as a promising solution to comply with "the right to be forgotten" regulations by enabling the removal of sensitive information upon request. However, this solution is not foolproof. The i…

本文如何被排名

报道来源 [1]

GraphToxin：从图解构中重建完整的未学习图

相关实体

相关话题