Anthropic 称新防御将 Claude 推理 token 窃取量削减 90% 至 99%
Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation
Anthropic 表示其新防御措施将 Claude 被提取的推理 token 量削减了 90% 至 99%，攻击者通过数十万个虚假账号网络大规模复制模型能力以训练自家小模型。Anthropic 点名中国公司智谱和月之暗面参与其中，称智谱为 GLM-5.3 从美国领先模型攫取网络能力，月之暗面则秘密将查询路由至 Claude。Anthropic 现已限制对 Claude 内部推理步骤的访问，运行检测提取尝试的分类器并自动封禁被标记账号，已有数万个账号被封，同时承认合法用户也会被误伤。
推荐理由
AI 评分 75
Anthropic 首次公开其反蒸馏措施与封禁规模，读者可了解模型能力被大规模窃取的攻防现状。
主题
正文
当前显示原文，中文全文译文尚未就绪。
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 fake accounts to pull it off.
Anthropic names Chinese companies Zhipu and Moonshot as participants. Zhipu allegedly siphoned cyber capabilities from leading US models for its GLM-5.3 model, while Moonshot secretly routed queries through Claude. The stolen capabilities could end up in foreign military and surveillance systems.
Anthropic now restricts access to Claude's internal reasoning steps, runs a classifier that detects extraction attempts, and automatically bans flagged accounts. Tens of thousands have already been banned. Anthropic is calling on other AI developers to adopt similar protections, although the company admits that legitimate users are getting caught up in the process too.