Anthropic announced on October 12, 2026 that it has deployed new defenses against “distillation attacks” — covert, industrial-scale campaigns to extract and replicate Claude’s capabilities without authorization. The company says early evidence shows the countermeasures, including restrictions on where Claude’s reasoning can go, a two-stage classifier with a false-positive rate below 0.1%, and stricter account limits and charges for blocked requests, have cut the data illicit distillers can harvest by roughly 90 to 99 percent.
