Anthropic ResearchAnthropic Research · Anthropic publishes anti-distillation defenses
Anthropic announced defenses against distillation attacks, saying early evidence shows the new methods reduce the amount of data a distiller obtains by roughly 90% to 99%, and the number of reasoning tokens extracted on the platform dropped to between 1/10 and 1/100 of previous levels. The defenses fall into three categories: using preserved thinking to prevent new API accounts from editing Claude's prior contexthip and making reasoning records visible only to the organization that produced them; using a two-stage classifier to intercept extraction attempts, with a false positive rate below 0.1%; and tightening limits on and banning accounts that repeatedly attempt extraction, charging for intercepted requests since September 24.
