OpenAI News·· 2026-09-30
Disrupting a coordinated model-distillation campaign
Disrupting a coordinated model-distillation campaign
AI summary
Learn how OpenAI disrupted a campaign to extract protected model reasoning and is strengthening defenses against adversarial distillation.
Selection record
Threshold 60Official, first-handFirst 58Second 58
Not admittedSum of both 116 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed:OpenAI模型蒸馏攻击与防御
- Same event
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: OpenAI News · openai.com