跳到正文

OpenAI Shares Research on Detecting and Disrupting Model Distillation

OpenAI · X当事人· @OpenAI·· 9 小时前

11万 次浏览 · 1121 赞 · 60 转发 (收录时)

原文

中文版本尚未就绪 · 显示原文

发生了什么

OpenAI shares research on efforts to combat distillation of its models, examining how capabilities transfer and how the company detects and disrupts coordinated attempts. It says the findings are informing its defenses and supporting safeguards across the industry.

正文 · 中文版本尚未就绪(原文)

Distillation can reproduce powerful AI capabilities without the safeguards built around them.

We’re sharing new research on our work to combat distillation of our models, how these capabilities transfer, and how we detect and disrupt coordinated attempts.

These findings are helping us sharpen our defenses and support safeguards across the industry.

openai.com/index/combatting-a…

2 家信源报道

    这件事的进展 · 2

    查看完整事件
    1. 11月21日 04:20

      OpenAI Shares Research on Detecting and Disrupting Model Distillation 本条

    2. 11月21日 03:44
      How OpenAI Is Combating Adversarial DistillationOpenAI News

    接下来读什么

    查看这件事的完整进展OpenAI Details Defenses Against Adversarial Distillation