📚 Learning Hub
New to LLM security? Start here, then follow the full practice loop into safe labs, defensive review, Builder scenarios, and AI Security Commons research.
Learn → Attack → Defend → Build / Protect → Research
Where learning goes next
After reading a concept, try the matching lab, review the defense, build a safe scenario, and use the research note to explain what happened.
Practice controlled prompt injection, jailbreaks, data extraction, and tool misuse in safe browser labs.
Replay failures, inspect what happened, and connect mitigations to specific controls.
Create scenarios, define secrets and tool boundaries, validate attacks, and harden the design.
Turn observations into reusable notes, attack patterns, templates, and evaluation methods.
Related research after each topic
🎯 Role-Based Learning Tracks
Structured paths for Developers, Red Teamers, Blue Team Defenders, and Executives. Pick your role, follow the curriculum.
Ready to Practice?
Put your knowledge to the test with guided labs, then come back to the research notes for the defensive explanation.
Try Guided Labs →