Threat modeling card game: Enables teams to collaboratively identify and discuss machine learning security risks
Based on BIML and OWASP research: Ensures alignment with established security frameworks for AI/ML systems
Four threat categories: Organizes risks into dataset, model, input, output, and system-wide categories for structured analysis
No specialist AI security expertise required: Accessible for mixed teams to explore threats together
Interactive and educational: Designed for workshops, training, and continuous learning
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 identifie