OpenAI said on September 30, 2026 that it identified and disrupted a coordinated campaign attempting to extract protected reasoning from its models. The company describes this as adversarial distillation: unauthorized use of a model's outputs or reasoning to help train or reproduce another model.
OpenAI says the operators did not break encryption, compromise a database or gain direct access to stored user conversations. Instead, the company says they manipulated model interactions so that protected reasoning could appear in forms visible to the requester. This report should not be presented as a conventional database breach.
The company reports that the activity began July 1. On July 24 and 25, it observed 16,000 requests using a relevant extraction pattern from more than 4,000 users. Its investigation found related prompt-pattern activity across a cluster of more than 15,000 users, which it says it disrupted by July 28. OpenAI explicitly says these figures describe attempted, not necessarily successful, extractions.
OpenAI attributes a core cluster to individuals associated with Moonshot AI, the developer of Kimi, while saying it is unclear whether all observed operators came from one actor. That is OpenAI's assessment, not independently established attribution by Next Tech Signal.
OpenAI says its response included account restrictions, stronger signup and infrastructure controls, monitoring, and technical protections for hidden reasoning. It also shared findings with industry partners through the Frontier Model Forum. The company says mitigation and investigation continue; it does not claim the entire attack class is permanently solved.
Source: https://openai.com/index/disrupting-a-coordinated-model-distillation-campaign/