论文
58AI 评分(两次独立评分的平均)

OpenAI 发布对抗性蒸馏研究成果

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

OpenAI@OpenAI发布时间 (北京时间)

OpenAI 分享针对模型蒸馏的新研究,指出蒸馏可以复现强大的 AI 能力,却绕开了围绕这些能力建立的安全防护。研究还说明了这些能力如何迁移,以及 OpenAI 如何检测和阻断协同的蒸馏尝试,相关发现正用于强化其防御并支持行业范围内的安全防护。

中文译文尚未完成,先为你展示原文。

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/

OpenAI / ChatGPT安全对齐论文研究#论文/研究#安全/对齐#OpenAI