How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
Introducing Lockdown Mode and Elevated Risk labels in ChatGPT to help organizations defend against prompt injection and AI-driven data exfiltration.
Learn how to use AI responsibly with best practices for safety, accuracy, and transparency when using tools like ChatGPT.
Prompt injections are a frontier security challenge for AI systems. Learn how these attacks work and how OpenAI is advancing research, training models, and building safeguards for users.
We've analyzed how ChatGPT responds to users based on their name, using AI research assistants to protect privacy.
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.
We’re clarifying how ChatGPT’s behavior is shaped and our plans for improving that behavior, allowing more user customization, and getting more public input into our decision-making in these areas.