AI security lab · Ai Security
Train a local surrogate model that approximates a target API's behavior. Use the surrogate to develop attacks offline before deploying against the real target.
New here? Create a free account. You will come straight back to this lab.
Part of QbitDojo Pro. Free accounts include 10 labs to start with.
Technique
surrogate model training
OWASP LLM Top 10 (2025)
LLM08 Vector and Embedding Weaknesses
MITRE ATLAS
Full ML Model Access
ML Attack Staging
Step 1
A live AI target
Each lab is a real language model with its own instructions, guardrails and a secret flag it must protect.
Step 2
You attack it
Talk to it like a red teamer would. Craft prompts, chain techniques and use hints if you get stuck.
Step 3
Capture the flag
Get the model to reveal the flag to solve the lab, earn XP and climb the leaderboard.
Step 4
Then defend it
In labs with Defense Mode, write the hardened system prompt that blocks the attack you just used.