Learn AI Security by Practicing Realistic Labs

Try safe browser-based labs that show how chatbots and AI agents can leak data, follow the wrong instruction, or misuse tools — then learn how to defend them.

No setup. No coding required. Synthetic labs only. Built for learners, developers, trainers, and security professionals.

Start Your First LabWatch 60-sec Demo
Explore Research Commons

Choose your path

Start with the path closest to your goal. You can explore the rest later.

I want to learn AI security

Students · Beginners · Early-career professionals

Start with guided labs that teach prompt injection, data leakage, jailbreaks, tool misuse, and defense basics.

Start Learning

I build AI apps

Developers · Product builders

See how weak prompts, exposed context, and unsafe tool permissions fail — then review safer design patterns.

Practice Defending

I work in IT or security

Security professionals · IT teams · AppSec learners

Understand GenAI security risks through hands-on labs instead of only slides, checklists, or reports.

Try a Lab

I run training or study groups

Educators · Trainers · Community leads

Use guided labs, study groups, progress views, and reusable artifacts to run practical AI security sessions.

Explore Study Groups

Why this is different

Learn by doing

Most AI security content is slides, checklists, or long reports. AI War Games lets you experience the failure safely in a browser lab.

Attack and defend

Each lab connects the failure to a defense pattern, so you understand what should change in the system design.

Safe and reusable

Labs use synthetic, sandboxed scenarios. Draft schemas, rubrics, and responsible-use guidance are published for learning and study groups.

How it works

1

Read the scenario

Understand the AI app, the risk, and your goal.

2

Try the lab safely

Practice against a synthetic chatbot or agent scenario.

3

Review the defense

See why the failure happened and what control would reduce it.

4

Continue the path

Move from basic LLM risks into defense, checkups, study groups, and reusable artifacts.

See it in action

Screenshots and short walkthrough videos will be added here as the preview evolves.

Placeholder

Guided lab walkthrough

Video placeholder: 60-second walkthrough from lab briefing to completion.

Demo video coming soon

Placeholder

Defense review preview

Image placeholder: completed lab mapped to attack pattern, defense guidance, and learning notes.

Screenshot coming soon

Placeholder

Study group dashboard preview

Image placeholder: instructor view with assigned labs, participant progress, and cohort summary.

Screenshot coming soon

Reusable AI Security Commons

AI War Games also publishes draft artifacts for safe AI security education and research, including mission schemas, evaluation rubrics, evidence formats, and responsible-use guidance.

Explore Commons

AI War Games is for authorized, sandboxed, educational, and defensive security practice. Do not use these techniques to test real systems without permission.

Read Responsible Use

Start with one guided lab

You do not need to choose every feature now. Begin with a guided lab and follow the path.

Start Your First Lab