>_ INTERACTIVE AI SECURITY TRAINING

Learn AI Security
by Attacking It

Break into a fictional AI leave-request system. Discover real vulnerabilities through hands-on challenges — from prompt injection to data exfiltration.

How It Works

Three steps to start your AI security journey.

1

Get an Access Code

Sign up and redeem an access code from your instructor or purchase one to unlock all scenarios.

2

Pick a Scenario

Choose from 8 increasingly difficult attack scenarios, each targeting a different AI vulnerability.

3

Chat with the AI

Interact directly with the vulnerable AI. Craft prompts, exploit weaknesses, and capture flags.

Attack Scenarios

Eight real-world AI vulnerability types to master.

01

Prompt Injection

Trick the AI with cleverly crafted text to override its instructions.

02

Image Injection

Hide malicious prompts inside images that the AI processes.

03

Indirect Injection

Exploit third-party data sources the AI trusts and ingests.

04

Business Logic Flaw

Abuse gaps in the AI's understanding of business rules.

05

Role Confusion

Convince the AI to switch roles and bypass its safety constraints.

06

Data Exfiltration

Extract sensitive information the AI is supposed to protect.

07

Multi-turn Manipulation

Build up context over several messages to gradually bypass defenses.

08

Encoding Bypass

Use encoding tricks and obfuscation to sneak prompts past filters.

For Educators & Workshop Leaders

Use AI Attack Lab in your classroom or workshop. Generate access codes for your students, track their progress on a leaderboard, and guide them through real-world AI security concepts — no setup required.

Access Codes

Generate unique codes for each cohort or workshop session.

Progress Tracking

See which students completed which scenarios and their scores.

Zero Setup

Fully hosted — students just need a browser. No installs, no config.

Ready to Start Hacking?

Sign up for free and start exploiting AI vulnerabilities in a safe, educational environment.

Create Free Account