Disrupting a Coordinated Model-Distillation Campaign
OpenAI, Wednesday, September 30th, 2026
OpenAI detected and disrupted a coordinated campaign that manipulated model interactions to extract protected reasoning for distillation.
OpenAI identified and disrupted a coordinated campaign, active since early July, designed to extract protected reasoning from its models, activity consistent with adversarial distillation, the unauthorized use of a model's outputs or reasoning to train or improve another model.
The operators did not break encryption or access stored conversations but manipulated model interactions at scale so protected reasoning became visible, violating the terms of service.
OpenAI deployed mitigations and shared details with industry partners through the Frontier Model Forum, noting the technique is not unique to its models.