OpenAI has described a layered approach to adversarial distillation that combines model training, safeguards, detection and enforcement, the company said.[1] OpenAI said the approach is meant to protect against capability extraction, meaning attempts by others to pull out what its models can do.[1] OpenAI says its layered approach to adversarial distillation combines model training, safeguards, detection, and enforcement to protect against capability extraction.[1]
OpenAI outlines layered defences against attempts to extract its models' abilities
OpenAI says the approach combines model training, safeguards, detection and enforcement to stop others pulling out what its models can do.
1 primary · 0 independent · 0 commentary · 1 vendorSources
- Combatting adversarial distillation OpenAI PrimaryVendor