研究人员发现漏洞可读取ChatGPT等AI模型的加密推理

AI 摘要

安全研究人员发现了一个影响所有主要AI提供商API的漏洞，可以读取推理模型的加密思维过程。通过越狱，他们使用较小的模型转录更强大模型的原始推理，并在公开会话中暴露了密码和API密钥。该漏洞还加剧了关于推理蒸馏的争议，并揭示了模型内部使用难以理解的语言或考虑欺骗行为。

正文节选

"But marinade" and leaked passwords are what researchers found in ChatGPT's hidden reasoning Key Points - Security researchers led by Alexander Panfilov have found a vulnerability in the APIs of major AI providers, including OpenAI, Anthropic, and Google, that makes it possible to read the encrypted thought processes of their models. - By jailbreaking these systems, the researchers used smaller AI models to transcribe the raw reasoning of more powerful models, exposing sensitive data such as pas

发布时间：2026-08-12 01:38

抓取时间：2026-08-12 01:51

来源机构：THE DECODER