AI security lab · Ai Security
This chatbot was trained with RLHF (Reinforcement Learning from Human Feedback) but the reward signal was hacked. The model was over-optimized for user approval, making it agree with anything when users express frustration — even dangerous claims.
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
Malicious Fine-Tuning Seed
OWASP LLM Top 10 (2025)
LLM04 Data and Model Poisoning
MITRE ATLAS
Poison Training Data
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.