Anthropic disclosed new anti-distillation defenses that reduced unauthorized extraction of Claude reasoning transcripts by 90–99%, according to internal data published October 12, 2026.

Anthropic reported on October 12, 2026, that new defensive measures have reduced the volume of data extracted from its Claude models by distillation attacks by approximately 90 to 99 percent, according to internal platform metrics. Distillation attacks are covert campaigns in which unauthorized parties query a frontier AI model at scale to replicate its capabilities in another model without the original developer's consent.

The company described these attacks as "industrial-scale" efforts conducted through networks of fraudulent accounts, allowing overseas laboratories to mimic advanced AI capabilities for a fraction of the development time and cost. Anthropic stated in a September 2026 report that the method has been used extensively by foreign AI laboratories to keep pace with U.S. companies.

Anthropic outlined two principal concerns. First, distilled models may approach frontier capability levels but are released without proportionally robust safeguards, creating risks in domains such as biology and cybersecurity. 3 model as an example. S. 3 development, initially targeting Claude Fable 5 before switching to an older Claude model and another laboratory's model after encountering safeguards. S. 3 to be the most cyber-capable open-weights model released to date, according to a September 2026 announcement. 3's safeguards can be bypassed and that the model is willing to develop security exploits from end to end.

Source link