English(EN) A Novel Semantic Manifold Alignment Attack against Embedding-to-Embedding Obfuscation in Privacy-Preserving LLMs

新的攻击方法针对隐私保护大语言模型的嵌入混淆

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-06 17:45

研究人员开发了一种名为代理流形对齐（PMA）的新攻击方法，该方法针对隐私保护大语言模型（LLMs）中使用的嵌入到嵌入混淆技术。这些混淆方法旨在通过本地转换嵌入来保护敏感查询，但它们缺乏强大的密码学保证。PMA将混淆后的向量流视为一个翻译任务，使用Word2Vec对共现模式进行建模以创建代理嵌入，然后对齐它们的流形以重建原始明文。 AI

影响这项研究突显了当前大语言模型隐私技术的潜在漏洞，表明需要更强大的密码学保证。

排序理由学术论文，详细介绍了针对大语言模型隐私技术的新颖攻击方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了针对大语言模型隐私技术的新颖攻击方法。[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: 31 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。

报道来源 [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-09-06 17:45

一种新颖的语义流形对齐攻击，用于隐私保护大语言模型中的嵌入到嵌入式混淆

With the widespread applications of large language models (LLMs), privacy-preserving inference has become increasingly essential for sensitive queries. To balance privacy and utility, a series of lightweight obfuscation approaches has recently been proposed, where users locally t…

本文如何被排名

报道来源 [1]

一种新颖的语义流形对齐攻击，用于隐私保护大语言模型中的嵌入到嵌入式混淆

相关实体

相关话题