Anthropic (X)· AnthropicAI·· 10 天前AI 评分43
Anthropic 详解 Claude 蒸馏攻击防御进展
Over the last few months, we’ve made significant progress in reducing the effectiveness of distillation attacks against Claude.
AI 导读
过去几个月，我们在降低针对 Claude 的蒸馏攻击有效性方面取得了重大进展。 在此文中，我们解释了具体方式：https://www.anthropic.com/research/distillation-defenses
来源：Anthropic (X) · x.com