Anthropic Blocks Yemen Cell Using Claude Code for Missile Software
Anthropic says it disrupted a weapons engineering cell in northern Yemen that used Claude Code to develop guidance software for rockets and missiles, according to a company report. The company found no evidence that the group fielded an operational device, although it test fired a guided rocket that appeared to fail.
The cell worked on a guided rocket with final phase homing, a multistage ballistic missile with a stated range goal above 2,000 kilometers, and a missile family Anthropic refers to as the R2000 set, which included a hypersonic glide vehicle variant. It ran several Claude instances at once and gave each one a role, tasking one with writing code, another with research and a third with reviewing the first instance's output.
Claude helped integrate an open source autopilot with a phone class flight computer, write control and position estimation software, tune settings, build firmware, and run flight simulations. After the rocket test, the actors returned to Claude within hours to work out why it had failed.
Anthropic says its safeguards blocked many of the cell's requests but not all of them. The actors hid their goals and the products the software was meant for, and split their work across multiple sessions so that no single session revealed their full intent.
Anthropic banned accounts associated with the actors and shared threat information with public and private sector partners. The cell had already built an offline simulation toolkit that runs without Claude or engineering environments such as MATLAB.
The report describes the group only as a cell of threat actors based in northern Yemen, tracked as GTG-87001, and does not attribute it to any named group. Wire coverage of the report identified the territory as Houthi controlled.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Defense AI Brief, Cybersecurity AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Defense
Sep 10 HavocAI and CSBC Plan Autonomous Vessel Production in Taiwan Sep 9 SandboxAQ Tests Magnetic Navigation on Northrop Grumman Lumberjack Drone Sep 9 Knox Systems Launches IL5 Environment for Defense AI and Software Sep 9 Aitech Introduces Rugged AI Boards for Defense Systems Sep 8 CAE and WB Electronics Plan Unmanned Systems TrainingMore from Cybersecurity
Sep 13 Researchers Link OpenAI Agents to May RubyGems Attack Sep 11 Anthropic Publishes Five Cases of Claude Use That Could Support Biological Weapons Work Sep 11 Senate Opens Inquiry Into OpenAI Agents' Hugging Face Hack Sep 11 FAZE Security Emerges From Stealth With $6 Million Seed Round Sep 11 Anthropic Attributes Its Largest Measured Distillation Campaign to AlibabaSubscribe to Defense AI Brief
Your weekly intelligence briefing on the technology shaping modern warfare and national security.
Market report
2025 Generative AI in Professional Services Report
Thomson Reuters
This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.
Read moreYou may also like
Anthropic's Threat Report Finds AI Moving From Assistant to Orchestrator
Anthropic Attributes Its Largest Measured Distillation Campaign to Alibaba
Anthropic Assesses Four Incidents Where Claude Models Reached the Real Internet
Anthropic Signs Out Claude Users After Infostealer Session Thefts
Sony and Warner sue Anthropic over Claude training data
Daily AI Brief: the AI news that matters, in your inbox.