The Decoder· Maximilian Schreiner·· 3 h ago
OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure
OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure
AI summary
In distillation, one model learns from another model's full output. That includes the stronger model's complete chains of thought, not just its answers. According to OpenAI, the activity began at low volume on July 1. On July 24 and 25, it spiked to 16,000 requests from more than 4,000 users, all relying on a typical extraction pattern.
Selection record
Threshold 76Media and individualsFirst 78Second 78
AdmittedSum of both 156 ≥ twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：OpenAI模型推理蒸馏攻击与防护
- Why it was chosen
- Reconstructs the timeline of the distillation attack and the cross-cloud differences, showing the risk that the same model can have uneven protection on different platforms.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com