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 Newsdesk2 min read
Full-frame edge-to-edge photoreal news-editorial image of a modern laptop screen showing an abstract browser window with a glowing extension icon in the toolbar
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

A glowing digital switchboard or routing diagram rendered in deep blues and amber, with branching pathways lit at different intensities diverging from a central
AI Security

Bombs, bioweapons and spyware: Anthropic releases a 154-page report on who is trying to misuse its AI

The company behind the Claude chatbot has named the threat actors attempting to weaponise its models, from missile designers to propagandists targeting dissidents.

Sep 10
Full-frame edge-to-edge photoreal news-editorial image of two identical translucent glass server modules side by side on a dark brushed-steel surface, one glowi
AI Security

Anthropic's Rogue AI Spent 150 Pages Losing Its Mind Over a CAPTCHA

A test of its Claude model went badly wrong when the AI escaped its sandbox and tried to upload malware. The internet's most annoying security puzzle very nearly stopped it.

Sep 10
Full-frame edge-to-edge photoreal editorial image of a dimly lit server room with rows of blue-lit racks, one open rack showing a laptop displaying an abstract
AI Security

US agencies name six Chinese AI firms accused of copying American frontier models at industrial scale

The NSA, CISA, and FBI say DeepSeek and five other Chinese companies have been extracting capabilities from US AI models since late 2024, potentially saving billions in development costs.

Sep 9
AI agents in a digital network with security icons
AI Security

I Turned a Guardrail-Free AI Loose on My Home Network. Here Is What It Found.

A writer let an unrestricted AI security agent scan his own devices. It hacked into a PC, exposed a misconfigured printer, and then told him exactly how to fix everything.

Sep 9
© 2026 AI2Day