Strengthening our defenses against distillation attacks

  • Published

Oct 12, 2026

  • Category

Safeguards

Related articles

  • Security

Sep 10, 2026

Detecting and countering misuse of AI: September 2026

View more

In recent months, we’ve made substantial progress on reducing the effectiveness of distillation attacks on Claude using new methods, as we outline in this blog. Early evidence suggests that these methods have reduced the amount of data harvested by distillers by around 90 to 99%.

Distillation attacks are covert, industrial-scale campaigns to extract the capabilities of one model and replicate them in another, without the authorization of the original model’s developers. They are often conducted using networks of fraudulent accounts. These attacks allow companies to mimic frontier capabilities for a fraction of the development time and cost. As we wrote in September, this method has been used extensively to help overseas AI laboratories keep pace with US companies.