Anthropic 发布其迄今最详细的威胁情报报告，覆盖网络攻击、影响行动、监控、生物和武器等滥用场景，并称已阻断报告中每一项行动。转发者指出，报告显示与伊朗国家关联的行为体使用 Claude 构建监控工具和恶意软件、识别异见人士、制作宣传材料，并分析公开信息以形成针对美国海军力量的打击建议。许多明显有害的请求被拦截，但这些行为体通过把项目拆分成看似无害的编码任务获得协助。
报告披露行为体把有害目标拆成看似无害的编码任务以绕过拦截，为理解 AI 滥用路径提供了具体案例。
That's why everyone at Frontier Labs is so worried about the near future. Anthropic's report shows how their enemies are already using Claude against the US:
According to Anthropic’s report, Iranian state-linked actors used Claude to build surveillance tools and malware, identify dissidents, produce propaganda, and analyze public information to develop targeting recommendations against US naval forces.
Many explicitly harmful requests were blocked, but actors obtained assistance by splitting projects into seemingly harmless coding tasks.
We're publishing our most detailed threat intelligence report to date. It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—and how we found and stopped them. We disrupted every operation in the report, and used the lessons from them to strengthen our safeguards. Where appropriate, we also shared what we found with authorities and other AI companies. These cases are not typical: we’re highlighting some of the most sophisticated misuse we’ve seen. But they’re especially important to discuss, because they show us where AI misuse is headed, where our safeguards work, and where they need to improve. We’re publishing this report so others can spot the same activity on their own platforms, and so we can give the public a clearer view of how emerging threats develop. Read the report: https://t.co/0EJUnYEgfz在 X 查看被引用的帖子
来源：@kimmonismus · x.com