Anthropic News · 23 天前精选模型评分67
Anthropic 公布 Claude 反蒸馏新防护措施
Strengthening our defenses against distillation attacks
导读
Anthropic 公布针对 Claude 的反蒸馏新防护措施，称早期证据显示蒸馏者获取的数据量下降约 90% 至 99%。这些措施包括限制推理内容在账号与模型间流转、用两阶段分类器拦截提取请求，以及对反复尝试提取的账号收紧限额并封禁。Anthropic 同时说明代价：部分开发者需更新集成，分类器误判率低于 0.1%，且自 9 月 24 日起对被拦截请求恢复计费。
推荐理由
Anthropic 公开了反蒸馏的三层防护做法与取舍，读者可据此了解模型厂商如何限制推理内容被批量提取。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：foundation-models，需要人工复核。
来源级别：官方一手
事件类型：安全事件
证据摘录
- “In response to the increasing sophistication and scale of these attacks, we’ve expanded and greatly strengthened our defenses against them.”
- “With Claude Fable 5.1 and Claude Opus 5.5, we introduced preserved thinking , a measure that prevents new API accounts (those created on or after August 31, 2026) from editing Claude’s prior context.”
- “Additionally, since September 24, we have resumed charging for requests that are blocked by our safeguards before Claude responds, in the specific areas (including distillation) where they have a <0.1% false positive rate.”
- “We haven’t met this goal completely: preserved thinking has required some developers to update their integrations, our classifiers can (in fewer than 0.1% of cases) misidentify or block benign requests, and we now charge users for those blocked requests.”
来源：Anthropic News · anthropic.com