
- Who
- OpenAI
- What
- details its defenses against adversarial distillation and protected reasoning extraction
What happened
OpenAI details its defenses against attempts to extract protected reasoning and use it to train models without comparable safeguards. In an internal adaptive black-box evaluation aggregated across six attacker models, the average success rate for extracting reasoning from an earlier request fell from 54.0% on GPT-6 Astra with original safeguards to 0.2% on GPT-6.2 Astra with updated safeguards. OpenAI also describes request-level protections, campaign investigations, and enforcement.
Why it matters
GPT-6.2 Astra reduced the average success rate for extracting protected reasoning from an earlier request to 0.2%, from 54.0% on GPT-6 Astra; the comparison comes from an internal adaptive black-box evaluation aggregated across six attacker models.
