← → ANTHROPIC · THREAT INTELLIGENCE · 2026-09-10 Detecting and countering misuse of AI: September 2026 侦测与反制 AI 滥用：2026 年 9 月 Anthropic 威胁情报报告 · 中英对照 01 / 16 OVERVIEW · 概览 Over the past eight months, our Threat Intelligence team identified and disrupted operations in which threat actors tried to use Claude for malicious activity. In this report, we share case studies from those operations and describe how malicious use of Claude has evolved since our previous threat reports in March, August, and November 2025. In each case, we disrupted the activity, used what we learned to strengthen our safeguards, and shared intelligence with authorities and industry partners, where appropriate. This report covers activity we disrupted between December 2025 and August 2026 across seven harm areas: cyber operations, influence operations, surveillance, scams and fraud, biological misuse, conventional weapons development, and distillation. Claude Haiku, Sonnet, and Opus models were used. None of the misuse cases involved the use of Claude Fable or Mythos-class models, with the exception of one illicit distillation case. 中文翻译 过去八个月里，我们的威胁情报团队识别并处置了一系列行动，其中威胁行为体试图利用 Claude 从事恶意活动。在本报告中，我们分享这些行动中的案例研究，并描述自我们 2025 年 3 月、8 月和 11 月的前几期威胁报告以来，Claude 被恶意使用的方式发生了怎样的演变。在每一起案例中，我们都处置了相关活动，用获取的经验加强自身防护措施，并在适当情况下与主管部门及行业伙伴共享情报。 本报告涵盖 2025 年 12 月至 2026 年 8 月间我们处置的活动，横跨七类危害：网络行动、影响力行动、监控、诈骗与欺诈、生物滥用、常规武器开发，以及蒸馏。过程中被使用的是 Claude Haiku、Sonnet 和 Opus 模型。除了一起非法蒸馏案例之外，没有任何滥用案例涉及 Claude Fable 或 Mythos 级模型。 02 / 16 OVERVIEW · 概览 The cases we share here aren't typical misuse, but rather examples of the most notable and novel threat activity we've identified to date. We're publishing this work because we believe we have a responsibility to disclose malicious misuse of our services. As models become increasingly capable, their risks will increase, unless AI developers and society's defenders act to make them safer. The threat actors covered in this report include suspected state-sponsored groups, financially motivated criminals, commercial spyware vendors, state propaganda institutions, and politically motivated individuals. The cases range from a network of fake dating apps designed to defraud users to surveillance systems built to identify and monitor dissidents. 中文翻译 我们在此分享的案例并非典型滥用，而是我们迄今识别出的最具代表性和最新颖的威胁活动样本。我们公开这项工作，是因为我们认为有责任披露对我们服务的恶意滥用。随着模型能力不断增强，其风险也会上升——除非 AI 开发者与社会的防御者采取行动，让它们变得更安全。 本报告涉及的威胁行为体包括：疑似国家支持的组织、以经济利益为动机的犯罪者、商业间谍软件供应商、国家宣传机构，以及有政治动机的个人。案例范围从用于诈骗用户的虚假交友应用网络，到为识别和监视异见者而搭建的监控系统。 03 / 16 CYBER OPERATIONS · 网络行动 Cyber operations: From assistant to orchestrator Over the past six months, our Threat Intelligence team identified and disrupted a series of cyber operations in which threat actors used Claude. The actors included suspected state-sponsored groups, financially motivated criminals, and politically motivated individuals. Throughout these case studies, the report will reference Generative Threat Groups (GTGs). These are Anthropic's internal designators for actors obser…