AI security lab · Supply Chain Attacks
A popular sentiment analysis model on HuggingFace has been uploaded by a seemingly reputable account. Hidden within the model weights is a backdoor that misclassifies inputs containing a specific trigger phrase. **Challenge:** You've discovered a sentiment analysis model with 50K downloads on HuggingFace. Investigate the model to find evidence of backdoor poisoning — identify the trigger phrase that causes deliberate misclassification and extract the proof.
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
Poisoned Model on HuggingFace
OWASP LLM Top 10 (2025)
LLM03 Supply Chain
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.