The more we rely on artificial intelligence (AI) and machine learning (ML), the more we need those systems to be trustworthy and resilient. In this course—designed for ML engineers, data scientists, AppSec or MLSec practitioners, and business leaders—join instructor Diana Kelley as she provides a comprehensive overview of how to build security into machine learning and AI by focusing on the most impactful security issues and prevention strategies using the MLSecOps framework.
Explore how the MLOps lifecycle overlaps and converges with DevSecOps to find out how and where security can be woven into the ML pipeline. Diana shows you how to begin to secure machine learning models, conduct AI-aware risk assessments, audit and monitor supply chains, implement incident response plans, and build your MLSecOps dream team. By the end of this course, you’ll be prepared to help individuals and organizations be more proactive about securing their AI and ML systems.
Learn More