Lead story
Models & availability
Latest
← Feed
Copy✕ Close copy menu
Understanding prompt injections: a frontier security challenge
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.
Visit source ↗openai.com
- Announced
- 07 Nov 2025 11:30 UTC
- Detected
- 03 Aug 2026 21:11 UTC (+269d after)