detecting-and-preventing-distillation-attacks

Announcements Detecting and preventing distillation attacks Feb 23, 2026 We have identified industrial-scale campaigns by three AI laboratories—DeepSeek, Moonshot, and MiniMax—to illicitly extract Claude’s capabilities to improve their own models. These labs generated over 16 million exchanges with

Executive Summary

Announcements Detecting and preventing distillation attacks Feb 23, 2026 We have identified industrial-scale campaigns by three AI laboratories—DeepSeek, Moonshot, and MiniMax—to illicitly extract Claude’s capabilities to improve their own models. These labs generated over 16 million exchanges with Claude through approximately 24,000 fraudulent accounts, in violation of our terms of service and regional access restrictions. These labs used a technique called “distillation,” which involves traini

Key Insights

• Announcements Detecting and preventing distillation attacks Feb 23, 2026 We have identified industrial-scale campaigns by three AI laboratories—DeepSeek, Moonshot, and MiniMax—to illicitly extract Claude’s capabilities to improve their own models. These labs generated over 16 million exchanges with Claude through approximately 24,000 fraudulent accounts, in violation of our terms of service and regional access restrictions. These labs used a technique called “distillation,” which involves training a less capable model on the outputs of a stronger one. Distillation is a widely used and legitimate training method. For example, frontier AI labs routinely distill their own models to create smaller, cheaper versions for their customers. But distillation can also be used for illicit purposes: competitors can use it to acquire powerful capabilities from other labs in a fraction of the time, and at a fraction of the cost, that it would take to develop them independently. These campaigns are growing in intensity and sophistication. The window to act is narrow, and the threat extends beyond any single company or region. Addressing it will require rapid, coordinated action among industry players, policymakers, and the global AI community. Why distillation matters Illicitly distilled models lack necessary safeguards, creating significant national security risks. Anthropic and other US companies build systems that prevent state and non-state actors from using AI to, for example, develop bioweapons or carry out malicious cyber activities. Models built through illicit distillation are unlikely to retain those safeguards, meaning that dangerous capabilities can proliferate with many protections stripped out entirely. Foreign labs that distill American models can then feed these unprotected capabilities into military, intelligence, and surveillance systems—enabling authoritarian governments to deploy frontier AI for offensive cyber operations, disinformation campaigns, and mass surv

Technical Deep Dive

Announcements Detecting and preventing distillation attacks Feb 23, 2026 We have identified industrial-scale campaigns by three AI laboratories—DeepSeek, Moonshot, and MiniMax—to illicitly extract Claude’s capabilities to improve their own models. These labs generated over 16 million exchanges with Claude through approximately 24,000 fraudulent accounts, in violation of our terms of service and regional access restrictions. These labs used a technique called “distillation,” which involves training a less capable model on the outputs of a stronger one. Distillation is a widely used and legitimate training method. For example, frontier AI labs routinely distill their own models to create smaller, cheaper versions for their customers. But distillation can also be used for illicit purposes: competitors can use it to acquire powerful capabilities from other labs in a fraction of the time, and at a fraction of the cost, that it would take to develop them independently. These campaigns are growing in intensity and sophistication. The window to act is narrow, and the threat extends beyond any single company or region. Addressing it will require rapid, coordinated action among industry players, policymakers, and the global AI community. Why distillation matters Illicitly distilled models lack necessary safeguards, creating significant national security risks. Anthropic and other US companies build systems that prevent state and non-state actors from using AI to, for example, develop bioweapons or carry out malicious cyber activities. Models built through illicit distillation are unlikely to retain those safeguards, meaning that dangerous capabilities can proliferate with many protections stripped out entirely. Foreign labs that distill American models can then feed these unprotected capabilities into military, intelligence, and surveillance systems—enabling authoritarian governments to deploy frontier AI for offensive cyber operations, disinformation campaigns, and mass surv

Why This Matters

This article from Anthropic’s News team shares valuable insights into cutting-edge AI development, engineering best practices, and the future of AI systems. Essential reading for AI engineers and researchers.

Related Resources

• 📄 Read Full Article
• 🏢 Anthropic News

---

This post was automatically curated from Anthropic. Published on 2026-02-26T17:01:00.343Z.