English(EN) Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs

新的白盒攻击方法利用知识编辑来针对大型语言模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-19 04:00

研究人员开发了一种新的针对大型语言模型（LLM）的白盒攻击方法，该方法利用知识编辑技术。这种方法修改了现有的编辑框架，以整合直接从模型中检索到的关联知识，从而能够针对更广泛的主题类别进行攻击，而不仅仅是预定义的提示。实验表明，与以前的技术相比，该方法更有效，同时没有显著降低LLM的整体性能。 AI

影响这项研究引入了一种探测LLM漏洞的新颖方法，可能影响未来的安全和保障研究。

排序理由该集群包含一篇详细介绍攻击LLM新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 0 / 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攻击LLM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: 52 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Roman Maksimov, Vladimir Aletov, Vladimir Solodkin, Dmitry Bylinkin, Daniil Medyakov, Aleksandr Beznosikov · 2026-08-19 04:00

利用知识编辑中的关联上下文检索构建针对大型语言模型的白盒攻击

arXiv:2608.17836v1 Announce Type: new Abstract: As large language models (LLMs) are granted increasing autonomy, it is essential to investigate methods that can induce unsafe behavior. We propose a novel white-box attack inspired by locate-then-edit approaches from the field of K…