AI2Day

Anthropic Raises Alarm Over Distillation Attacks from China-Based AI Labs

Anthropic reveals a surge in distillation attacks on its AI models, targeting valuable capabilities and potentially aiding rival technologies.

AI2Day NewsdeskAsistido por IAPublicado Updated Editor: Lee Brown2 min read
A cybersecurity operations center monitoring AI model security threats, analysts tracking distillation attacks on display screens, maps showing attack origins f
Ilustración creada con IA. No es una fotografía de los hechos descritos.
Share

Key points

  • Anthropic reported nearly 200 million distillation attacks by China-based AI firms as of October 2023.
  • Alibaba led the attacks with 151 million exchanges between May and July 2026.
  • Moonshot AI's campaign allegedly involved requests from the Chinese military.

What happened?

Anthropic, an American AI company, has reported extensive distillation attacks from China-based AI companies. These attacks, which have intensified over several months, involve methods to bypass Anthropic's defenses and extract critical capabilities from their models. A distillation attack is a technique where attackers trick a model into revealing its

Latest AI Security stories

Illustration: a dark security operations desk at night
AI Security

Google's new Gemini 4 Carbon goes to cyber defenders first, not the public

The model claims zero successful prompt injections in Gray Swan's test and reaches security teams before developers or consumers see it.

Oct 28
Illustration: dense lines of green and white code scrolling across a dark monitor screen
AI Security

AI Found a Decade-Old Security Flaw in Millions of Websites. Here Is What That Means for You.

OpenAI's technology helped researchers discover critical vulnerabilities in PHP, the programming language that quietly powers a huge portion of the internet. Governments from the US to Japan are scrambling, and website owners face a hard deadline.

Oct 25
Illustration: A vast open-plan corporate server room at night, bathed in cool blue light
AI Security

Microsoft Is Treating AI Agents Like Insider Threats. Here Is the Plan.

A new security framework and admin console aim to give IT teams the same control over AI agents that they already have over human employees, before something goes wrong.

Oct 22
Illustration for the story: Open-Weight AI Models Are Losing Their Safety Guardrails in Under Three Days
AI Security

Open-Weight AI Models Are Losing Their Safety Guardrails in Under Three Days

A new report finds that stripped, unguarded versions of publicly released AI models appear online faster than ever, and some will walk a self-declared terrorist through bomb construction.

Oct 17
© 2026 AI2Day