aifollow.news
Back OpenAI 官方新闻
OpenAI 官方新闻· · Original publication time AI score20

OpenAI outlines a layered approach to adversarial distillationMachine translation

OpenAI介绍防范对抗性蒸馏的分层方法

AI-assisted summary

OpenAI describes an approach that combines model training, safeguards, detection, and enforcement to protect against capability extraction. The material does not specify how effective the measures are.

The complete source text is not yet available.

Read at the original source
Found an error? Send a correction