OpenAI 和 Hugging Face 应对 AI 模型评估期间发生的安全事件

发生了什么

OpenAI 和 Hugging Face 报告了 AI 模型评估期间发生的一起安全事件的初步调查结果，指出了先进的网络能力以及对防御方的影响。

A concrete security incident occurred during model evaluation involving advanced cyber capabilities, impacting organizational evaluation environments.

证据摘录

• A security incident occurred during AI model evaluation involving OpenAI and Hugging Face.
• The incident demonstrated advanced cyber capabilities and provided lessons for defenders.

严重度维度

来源引用

1. OpenAI and Hugging Face partner to address security incident during model evaluationOpenAI News · 2026-07-21 · primary