All News
Neural Networks

Continuously hardening ChatGPT Atlas against prompt injection

December 22, 20252 views1 min read

OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning. This proactive discover-and-patch loop helps identify novel exploits early and harden the browser agent’s defenses as AI becomes more agentic.

Want to try AI?

Compare the best neural networks in one place — for free

Go to neural networks
Share:
Источник: OpenAI Blog

Related News