AI Daybook
AI Daybook
Today's issue
Korean outletResearch

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.

#anthropic#security#model distillation
Read the originalaitimes.com · in Korean
See all →
Read the originalaitimes.com · in Korean