研究揭示可窃取并移植加密推理痕迹，引发隐私担忧

AI 摘要

一篇研究论文展示了如何通过重放加密的推理块，从Claude、GPT和Gemini等前沿模型中提取隐藏的推理痕迹，并成功移植到其他模型或会话中，从而显著提升开源模型性能。初步扫描约7000个公共痕迹发现62个API密钥、33个邮箱和33个密码等敏感数据泄露。该漏洞已负责任披露，部分已修复，但类似攻击仍可能发生。

正文节选

[AINews] How to steal a Reasoning Trace Speculative Decoding by any other name would distil as sweet It’s not very often that a paper breaks through to become headline story of the day. For understandable reasons both domestic and foreign, there is renewed interest in the Interpretability Venn Diagram of alignment, security, and chain of thought monitoring, so today’s paper could not have come at a better time: Since the o1 launch, frontier lab reasoning models have obscured their traces, with c

发布时间：2026-08-12 15:11

抓取时间：2026-08-12 15:18

来源机构：swyx and Latent Space