OpenAI says it intercepted distillation theft attack, but researchers say same method can still steal reasoning content of models like GPT-6 Astra on Azure
OpenAI said it intercepted a distillation theft campaign targeting its model reasoning chains in July; from July 24 to 25 there were 16000 requests from over 4000 users, with over 15000 associated accounts, which OpenAI linked to personnel related to Moonshot AI, and shut down on July 28.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original