Combatting adversarial distillation
- As frontier AI models become more capable, safeguards play an increasingly important role in how they can be used responsibly.
- Adversarial distillation creates a path for bad actors to reproduce these capabilities without appropriate safeguards.
- An actor may use a frontier model’s outputs without authorization to train another model with similar capabilities, then deploy it without comparable protections.
Unverified
- As frontier AI models become more capable, safeguards play an increasingly important role in how they can be used responsibly.
- Adversarial distillation creates a path for bad actors to reproduce these capabilities without appropriate safeguards.
- An actor may use a frontier model’s outputs without authorization to train another model with similar capabilities, then deploy it without comparable protections.
Sources: Openai