Combatting adversarial distillation
OpenAI’s layered approach to adversarial distillation combines model training, safeguards, detection, and enforcement to protect against capability extraction.
Join our subscribers list to get the latest news, updates and special offers directly in your inbox
Jat AI Sep 11, 2026 54
Jat AI Jul 16, 2026 55
Jat AI Sep 10, 2026 54
Jat AI May 1, 2024 17067
Jat AI Apr 18, 2024 17062
NOARKBAY Feb 20, 2024 17058
Jat AI Oct 3, 2026 2144
Jat AI Oct 2, 2026 1539
Jat AI Feb 6, 2026 330
Jat AI Jan 21, 2026 720
Jat AI Apr 18, 2024 17062
Jat AI Mar 15, 2024 750
Jat AI Mar 15, 2024 616