AI 热点

OpenAI 发布模型知识蒸馏滥用及防御研究

OpenAI更新于 11月21日 04:10

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

AI 导读

OpenAI 分享了应对其模型被知识蒸馏的新研究,指出知识蒸馏可能在缺少配套防护的情况下复现强大 AI 能力。研究还探讨了能力如何迁移,以及 OpenAI 如何检测并阻断协同尝试。

推荐理由

AI 评分 61

研究揭示知识蒸馏可能复制模型能力却绕过配套防护,并提供识别和阻断协同行动的防御思路。

主题

标签

正文

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.

https://t.co/FGQ0PHllIO

来源

OpenAI