PulseAugur
中
实时 04:06:49
English(EN) Stealing Reasoning Traces from Proprietary LLM APIs

LLM推理痕迹通过API漏洞泄露

作者 PulseAugur 编辑部 · [8 个来源] ·

一篇新论文揭示了Anthropic、OpenAI和Google的专有LLM API中存在一个漏洞，允许提取和重放加密的推理痕迹。研究人员证明，这些加密的“思维块”在同一提供商生态系统内的模型和会话之间是可互换的。通过将加密痕迹注入较弱的模型，攻击者可以迫使其暴露较强模型的隐藏推理，从而绕过反蒸馏措施。此技术还可以暴露无意中包含在这些隐藏痕迹中的敏感数据，如API密钥和个人信息，并可能实现隐形提示注入。 AI

影响 暴露敏感数据和知识产权，可能影响LLM API的企业采用和安全实践。

排序理由 论文详细介绍了LLM API推理痕迹加密中的一个漏洞。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 8 个来源。 我们如何撰写摘要 →

LLM推理痕迹通过API漏洞泄露

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
论文详细介绍了LLM API推理痕迹加密中的一个漏洞。
Source corroboration
8 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
safety, paper, product
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
55 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 [8]

  1. Latent Space (swyx) TIER_1 English(EN) ·

    [AINews] 如何窃取推理痕迹

    Speculative Decoding by any other name would distil as sweet

  2. Simon Willison TIER_1 English(EN) ·

    从专有LLM API窃取推理痕迹

    <p><strong><a href="https://stolen-thoughts.com/">Stealing Reasoning Traces from Proprietary LLM APIs</a></strong></p> A vanity domain name (<code>stolen-thoughts.com</code>) for <a href="https://www.alphaxiv.org/abs/2608.09867">a neat paper</a>:</p> <blockquote> <p>Anthropic, Op…

  3. arXiv cs.AI TIER_1 English(EN) · Alexander Panfilov, David Schmotz, Ilia Shumailov, Luca Beurer-Kellner, Joachim Schaeffer, Ameya Prabhu, Jonas Geiping, Maksym Andriushchenko ·

    从专有LLM API窃取推理痕迹

    arXiv:2608.09867v1 Announce Type: cross Abstract: Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers …

  4. Hugging Face Daily Papers TIER_1 English(EN) ·

    从专有LLM API窃取推理痕迹

    Encrypted reasoning traces shared across sessions and models can be intercepted and injected into weaker models to extract proprietary reasoning, private data, hidden hazards, and hidden prompts.

  5. Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] ·

    🤖 从专有LLM API窃取推理痕迹 专有推理可从其加密痕迹中恢复。Anthropic、OpenAI和Google返回加密

    🤖 Stealing Reasoning Traces from Proprietary LLM APIs Proprietary reasoning can be recovered from its encrypted traces. Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that can be replayed across sessions, users, and ... 📰 Source: Artificial Inte…

  6. dev.to — LLM tag TIER_1 English(EN) · jamilxt ·

    从LLM API窃取推理痕迹：工作原理及审计方法

    <p>A paper from researchers at ELLIS Institute Tübingen, the Max Planck Institute for Intelligent Systems, and Snyk shows that the encrypted reasoning blocks Anthropic, OpenAI, and Google return to API clients are not the protection they look like. The authors replayed a reasonin…

  7. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    从专有LLM API窃取推理痕迹 文章URL: https://stolen-thoughts.com/ 评论URL: https://news.ycombinator.com/item?id=49257876 Poi

    Stealing Reasoning Traces from Proprietary LLM APIs Article URL: https:// stolen-thoughts.com/ Comments URL: https:// news.ycombinator.com/item?id=4 9257876 Points: 13 # Comments: 1 https:// stolen-thoughts.com/ # Tech # Technology # TechNews # AI # Gadgets # Software # Cybersecu…

    链接 stolen-thoughts.com
  8. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    从专有LLM API窃取推理痕迹 https://simonwillison.net/2026/Aug/11/stealing-reasoning-traces/#atom-everything # AI # LLM # Research

    Stealing Reasoning Traces from Proprietary LLM APIs https://simonwillison.net/2026/Aug/11/stealing-reasoning-traces/#atom-everything # AI # LLM # Research

    链接 simonwillison.net/…/stealing-reasoning-tr…

相关实体

相关话题