Threat modeling workshop: what could possibly go wrong with an AI system?
Elias Brattli Sørensen, Developer & Security Engineer, Kantega SSO
About the session
In this workshop, we will demystify how machine learning systems actually work, and explore how a threat modeling game can help us engineer more secure machine learning systems.
We will do threat-modeling together using the game I have created in Elevation of MLsec: https://github.com/kantega/elevation-of-mlsec. The game has adopted the Berryville Institute of Machine Learning (BIML) risk framework into an extension of the well-known threat modeling game called Elevation of Privilege. Playing games is an excellent way to facilitate learning and collaboration in a fun and non-intimidating way. Learn to think more about risks so that you can use, build or integrate with AI in a safer and more responsible way.
Takeaways: Get an insight into how AI "actually works", an overview of risks with ML systems, and get started with threat modeling using a card game.
This is a workshop that should be fun and interesting for anyone involved in professional software projects. While no prior knowledge is required to participate, it is more relevant for those who work with the technical aspects of the software and its architecture. It should be even more relevant to developers or architects working directly with AI.
About the presenter
Developer & Security Engineer at Kantega SSO, engineering digital identity standards for secure authentication to the Atlassian ecosystem while facilitating and promoting secure software development practices.
M. Sc. in Computer Science at NTNU, researching usage of static analysis tools like Spotbugs to find vulnerabilities in OpenID Connect client implementations.
Passionate about software security, music and rock climbing.