Anthropic strengthens defenses against illegal model distillation, reducing data extraction by 90-99%
Original article in Korean앤트로픽, 불법 증류 차단 고강도 방어 체계 도입...“추출 시도 최대 99% 감축”
- Outlet
- AI Times
- Published
- Importance
- 4/5
Summary
Anthropic significantly strengthened Claude's defenses against illegal distillation attacks that steal the model's reasoning capabilities. New security measures reduced the amount of inference data attackers can collect by 90 to 99 percent compared to previous levels.