Elevation of Machine Learning (ML) Security Card Game

Created by Elias Brattli Sørensen, Elevation of MLSec is a threat modeling card game inspired by Adam Shostack’s Elevation of Privilege game, and based on the risk framework published by the Berryville Institute of Machine Learning (BIML). 

These playing cards portray risks associated with Machine Learning systems that have been identified by research groups. 

The cards are arranged in 4 threat categories (or "suits"). The ten components from the BIML-78 risk analysis are mapped to these 4 suits: 

1. Dataset risks (Raw, Training, Assembly)
2. Model risks (Algorithm, Evaluation, Model)
3. Input risks 
4. Output risks

The inference risks and system wide risks are applied to categories where the individual risk fits best. There are also a few LLM risks to give the deck a little flavour. 

Elevation of MLSec is © 2024 Kantega AS