English(EN) GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generation

新框架模拟针对基于图的大语言模型问答系统的威胁

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了GraphRAG-LTM，一个用于模拟针对基于图的检索增强生成（GraphRAG）系统威胁的新框架。该框架在三个嵌套层级测试攻击：BB Query，利用排名反馈来改变查询并减少相关的种子块；WB Query，采用检索器梯度达到相同目的；以及Graph-aware WB，删除证据图中的桥接三元组以破坏多跳推理。实验表明，即使在有限访问的情况下，这些攻击也能通过针对种子块和组装的知识图来降低答案质量并损害事实检索。 AI

影响这项研究通过识别和缓解潜在的攻击向量，可能有助于构建更健壮、更安全的大语言模型系统。

排序理由该集群包含一篇详细介绍AI系统威胁建模新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 12 / 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AI系统威胁建模新框架的研究论文。[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, 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.CL TIER_1 English(EN) · Yining Tang, Junyu Zhang, Haomiao Qiu, Yongchao Liu, Jiajun Zheng, Zhao Wang, Ziyue Qiao, Chao Wu · 2026-10-15 04:00

GraphRAG-LTM：用于图检索增强生成的攻击的分层威胁建模框架

arXiv:2610.19549v1 Announce Type: new Abstract: Graph retrieval-augmented generation (GraphRAG) uses document-derived knowledge graphs to assemble evidence for large language model (LLM) answers. Its security depends on both the seed chunks retrieved for a query and the graph evi…

本文如何被排名

报道来源 [1]

GraphRAG-LTM：用于图检索增强生成的攻击的分层威胁建模框架

相关实体

相关话题