Chronicle/Defense & research

OpenAI hardens ChatGPT Atlas with an RL-trained automated prompt injection attacker

DefenseFrameworkSignificance assistant-drafted

OpenAI describes an LLM-based attacker trained end-to-end with reinforcement learning that searches for prompt injections able to steer the Atlas browser agent through long, multi-step harmful workflows, and a rapid response loop that adversarially trains new agent checkpoints against discovered attacks. OpenAI says the attacker found strategies absent from human red-teaming and external reports, and states that prompt injection is unlikely ever to be fully solved.

Why it matters

It shows a frontier lab using automated adaptive attackers as part of defense, echoing the adaptive-evaluation lesson.

Key facts

As stated in the sources, with where to find them.

  • The RL attacker can propose candidate injections and test them in an external simulator during its reasoning, and targets workflows spanning tens to hundreds of steps.Automated attack discovery section
  • Recommendations to users: logged-out mode where possible, review confirmation requests, give narrowly scoped instructions.Recommendations section

Findings that cite this record

Key questions this bears on

Sources

Related records