Anthropic Reports Distillation Defenses Reduced Extracted Reasoning Tokens

본문 미리보기

Anthropic on October 12, 2026, detailed expanded and strengthened defenses against distillation attacks targeting Claude, saying early evidence suggests the new methods have reduced the amount of data harvested by distillers by around 90 to 99 percent. In the post, Strengthening our defenses against distillation attacks, the company defined distillation attacks as covert, industrial-scale campaigns to extract one model's capabilities and replicate them in another without authorization, often…