What's new
ModelsOpenAI

Combatting adversarial distillation

Reported by OpenAI, Friday, 20 November 2026, 10:00 UK time.

OpenAI's summary

OpenAI’s layered approach to adversarial distillation combines model training, safeguards, detection, and enforcement to protect against capability extraction.

Read the full story at OpenAI →

This story is in the daily edition for Friday 20 November 2026.

More AI news from the same day

Earlier stories about OpenAI