OpenAI on November 20, 2026 announced stronger defenses against adversarial distillation, reporting that the average success rate for adaptive attacks extracting protected 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. For extraction from the current request, the corresponding average fell from 22.9% to 0.9%, OpenAI reports. The adaptive black-box evaluation aggregates results across six attacker…
Read the original article:
OpenAI Strengthens GPT-6.2 Astra Against Reasoning Extraction
