English(EN) Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs

在 MoE 大语言模型中发现新的“结构化记忆”漏洞

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

研究人员在专家混合（MoE）大语言模型中发现了一种名为“结构化记忆”的新漏洞。该漏洞使模型不仅能记住其训练数据，还能记住处理这些数据的特定内部路径，从而创建独特的路由指纹。攻击者可以通过分析无条件生成输出来利用这一特性，即使没有原始训练数据的访问权限，也能恢复被记住的专家路径。这些发现对于分布式部署（如联邦学习和边缘-云系统）尤其令人担忧，因为路由信息会在多个信任边界暴露。 AI

影响这项研究突显了分布式大语言模型部署中潜在的安全风险，需要新的方法来检测受损模型。

排序理由该集群包含一篇详细介绍大语言模型新漏洞的学术论文。[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: 1 / 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大语言模型新漏洞的学术论文。[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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Fei Wang, Baochun Li, Bo Li · 2026-11-02 05:00

Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs

arXiv:2610.41039v1 Announce Type: new Abstract: As Mixture-of-Experts (MoE) large language models are increasingly deployed in distributed environments, from federated learning to edge-cloud systems, their architecture harbors an underexplored landscape of security vulnerabilitie…

本文如何被排名

报道来源 [1]

Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs

相关实体

相关话题