English(EN) MEASER: Malware embedding attacks on open-source LLMs

研究人员揭示 MEASER，一种针对开源大语言模型的新型恶意软件攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-04-28 04:00

研究人员开发了一种名为 MEASER 的新方法，用于在开源大语言模型中嵌入恶意软件。该技术针对特定参数注入恶意载荷和触发器，旨在逃避检测，即使在模型量化或微调后也能奏效。在几个流行大语言模型上的实验表明，MEASER 具有很高的隐蔽率，并且在不显著降低性能的情况下有效传递载荷。 AI

影响针对开源大语言模型的新攻击向量可能需要新的模型部署安全协议。

排序理由详细介绍针对开源大语言模型新攻击方法的学术论文。

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: Research; 详细介绍针对开源大语言模型新攻击方法的学术论文。
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: 162 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.AI TIER_1 English(EN) · Ming Tan, Wei Li, Hu Tao, Hailong Ma, Aodi Liu, Qian Chen, Zilong Wang · 2026-04-28 04:00

MEASER：开源大模型中的恶意软件嵌入攻击

arXiv:2510.10486v2 Announce Type: replace-cross Abstract: Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharing nature. Although full access to source c…