OpenAI· @OpenAI · X·· 1 天前AI 评分58
AI 导读
OpenAI 分享关于对抗模型蒸馏的新研究,指出蒸馏可以复制强大的 AI 能力,却绕开围绕这些能力建立的防护措施。研究还说明了这些能力如何被转移,以及 OpenAI 如何检测和阻断有组织的蒸馏尝试,相关发现正用于强化其防御并支持行业防护。
正文 · 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.
https://openai.com/index/combatting-adversarial-distillation/
来源:OpenAI · x.com