OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure
OpenAI says it halted a coordinated campaign in which more than 15,000 accounts attempted to copy the hidden reasoning of its models, according to The Decoder. The company ties part of the activity to people connected to Moonshot AI.
According to the report, researchers found that the same attack continued to work on Microsoft Azure for weeks, including against the new GPT-6 Astra. OpenAI's protections so far do not appear to extend to the cloud platforms that also sell its models, the report states.
The account figures, the attribution, and the reported duration of the Azure exposure all come from OpenAI and the researchers cited in the report.
Based on reporting from the original publisher. Visit the source for full context and later updates.
Publisher excerpt
OpenAI says it stopped a coordinated campaign in which more than 15,000 accounts tried to copy the hidden reasoning of its models. The company ties part of the activity to people connected to Moonshot AI. But researchers found that the same attack kept working on Microsoft Azure for weeks, even against the new GPT-6 Astra. So far, OpenAI's protections don't seem to extend to the cloud platforms that also sell its models. The article OpenAI says it stopped a campaign to steal its models' reasoning, but the trick sti