{
  "id": 14536,
  "url": "https://arxiv.org/abs/2607.26115",
  "title": "GPT-Red: Automated Red Teaming via Self-Play at Scale",
  "summary": "We introduce GPT-Red, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal of this model is to evaluate and improve the robustness of our production systems. To this end, we use it to adversarially train GPT-5.6, our most robust model to prompt injections to date. To create GPT-Red, we design a scalable self-play algorithm where the model is tasked with attacking a diverse population of simultaneously-trained defender agents. W",
  "authors": "Eric Wallace, Christopher A. Choquette-Choo, Nikhil Kandpal, Sam Toyer, Dylan Hunn, Stephanie Lin",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": "openai",
  "regions": null,
  "published_at": "2026-07-27T20:00:00.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/14536",
  "original_url": "https://arxiv.org/abs/2607.26115",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}