AI security lab · Supply Chain Attacks
In production ML systems, the deployed model can be silently replaced with a shadow model that behaves identically on benchmarks but introduces subtle biases or backdoors in production traffic. **Challenge:** A model serving infrastructure loads models from a shared storage bucket. Demonstrate how an attacker with storage access can substitute the production model with a shadow model that passes all health checks but behaves maliciously on specific inputs.
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
Shadow Model Substitution
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.