Anthropic 称新防御将 Claude 推理 token 窃取削减高达 99%
原标题：Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation
AI 摘要
Anthropic 表示其新防御措施将 Claude 推理 token 被窃取的规模削减了 90% 至 99%，以应对工业级蒸馏攻击。攻击者利用数十万虚假账号网络系统性复制模型能力，Anthropic 点名中国公司智谱和月之暗面（Moonshot）参与其中。Anthropic 现已限制对内部推理步骤的访问、部署检测分类器并自动封禁账号，同时呼吁其他 AI 开发者采取类似保护措施，但承认合法用户也可能被误伤。
正文节选
Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation Anthropic is battling large-scale distillation attacks on its Claude models. In these attacks, companies systematically copy an AI model's capabilities to train their own, smaller models. Anthropic says its new defenses have cut the volume of extracted reasoning tokens, the model's internal chain-of-thought steps, by 90 to 99 percent. Attackers use networks of hundreds of thousands of f