OpenAI says it detected and blocked a coordinated model-distillation attack

Disrupting a coordinated model-distillation campaign

OpenAI says it found and blocked a coordinated distillation attack that first appeared in the first week of July, with attackers trying to extract protected reasoning from its models. Peaks came on July 24 and 25: 16,000 requests from more than 4,000 users, with prompt-pattern activity tied to over 15,000 users. OpenAI says it fully blocked the activity by July 28.

Why it matters: OpenAI disclosed a coordinated distillation attack on protected model reasoning, with a timeline and response, showing how such attacks work and how they are defended.