Managing Vulnerabilities in Machine Learning and Artificial Intelligence Systems
June 2021 • Podcast
Allen Householder, Jonathan Spring, and Nathan VanHoudnos discuss how to manage vulnerabilities in AI/ML systems.
“If you are using machine learning (ML), you are using it to solve a task because you want something done. If the doing or not properly doing of that task has an implication for your security posture, then you need to think about what the failure modes of the machine learning system imply for security. You have to think about your security policies, and then you have to think about making sure that those security policies are met when you introduce this new shiny ML thing into it.”
Software Engineering Institute
The current paradigm of vulnerability management might have to adapt to include machine learning (ML) and artificial intelligence (AI) systems. In this SEI Podcast, Allen Householder, Jonathan Spring, and Nathan VanHoudnos discuss how to manage vulnerabilities in AI/ML systems.