Skip to main content
Latest Update
2026-11-20 11:33 UTC

OpenAI details latest defenses against adversarial distillation

OpenAI details latest defenses against adversarial distillation

According to OpenAI, new research outlines how adversarial distillation can replicate model capabilities without safeguards and details methods to detect, disrupt, and prevent coordinated attempts.

Source

Analysis

OpenAI announced new research on November 20, 2026, focused on combating distillation of its models.

According to OpenAI, distillation can reproduce powerful AI capabilities without the safeguards built around them, and the research examines how these capabilities transfer along with methods to detect and disrupt coordinated attempts, sharpening defenses and supporting industry safeguards.

OpenAI

@OpenAI

Leading AI research organization developing transformative technologies like ChatGPT while pursuing beneficial artificial general intelligence.