automated-red-teaming

Tag

Cards List
#automated-red-teaming

GPT-Red: Automated Red Teaming via Self-Play at Scale

Hugging Face Daily Papers · 4d ago Cached

This paper introduces GPT-Red, an automated red-teaming agent trained via self-play at scale to discover novel prompt injection attacks against frontier LLMs, and uses it to adversarially train GPT-5.6, achieving the largest documented LLM safety training run.

0 favorites 0 likes
← Back to home

Submit Feedback