English(EN) S-GAP: Stealthy Graph Attack Primitives for Graph Large Language Models

新的S-GAP框架增强了对GraphLLMs的隐蔽对抗性攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 04:00

研究人员推出了一种名为S-GAP的新型框架，旨在增强对图大语言模型（GraphLLMs）的对抗性攻击。S-GAP将文本和结构扰动统一为单一的“图攻击原语”（GAP），以提高攻击的隐蔽性和有效性。该系统采用多智能体方法进行迭代优化和代理评估，在各种数据集和模型上，攻击成功率平均比现有方法提高了7.02%。 AI

影响引入了一种更有效的方法来评估和潜在地提高GraphLLMs对抗操纵的鲁棒性。

排序理由关于图大语言模型对抗攻击新方法的学术论文。[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: 20 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于图大语言模型对抗攻击新方法的学术论文。[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.AI TIER_1 English(EN) · Wenda Li, Tongya Zheng, Shunyu Liu, Hanyang Yuan, Kaixuan Chen, Yu Wang, Yuchen Ying, Haoze Jiang, Huan Li, Gang Chen, Zujie Ren · 2026-10-19 04:00

S-GAP：用于图大语言模型的隐蔽图攻击原语

arXiv:2610.23465v1 Announce Type: new Abstract: Graph Large Language Models (GraphLLMs) enable powerful semantic understanding and reasoning over Text-Attributed Graphs (TAGs), while their semantic reasoning may exhibit vulnerabilities to perturbations in node text and graph stru…

本文如何被排名

报道来源 [1]

S-GAP：用于图大语言模型的隐蔽图攻击原语

相关实体

相关话题