OpenAI claims to thwart model distillation attack tied to Moonshot

T2Covered by 1 source · first reported by JP/KR/TW: Korea Herald / Taipei Times / DigiTimes at 01 Oct, 02:51 UTC

OpenAI said it detected and blocked an organized adversarial distillation attack, with some activity linked to Chinese AI startup Moonshot AI. The company said it first spotted the effort on July 1 and saw a peak on July 24 and 25, when it detected about 16,000 related requests from more than 4,000…

ai

Sources

• T2OpenAI claims to thwart model distillation attack tied to MoonshotJP/KR/TW: Korea Herald / Taipei Times / DigiTimes01 Oct, 02:51