OpenAI · Lab blog · 20 Nov 2026 UTC

OpenAI logo

Combatting adversarial distillation

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

This is the official summary from OpenAI. Read the full post on their site.

Read on OpenAI

Combatting adversarial distillation · Maker Crown