Securing the AI/ML Development Lifecycle: A Practical Guide to Secure AI Engineering

This course explores security throughout the lifecycle of ML/AI systems. Instructor Ed Moyle covers process-aware approaches for “building security in” including AISecOps and MLSecOps. Additionally, Ed explores mechanisms such as AI bills of materials (BOMs) and ways to adapt traditional application/product security efforts to AI-enabled products and software.

Learning objectives

• Analyze security requirements specific to AI/ML systems throughout their development and deployment lifecycle.
• Evaluate traditional security frameworks for adaptation into AI-enabled applications and MLOps/MLSecOps processes.
• Design process-aware security approaches for AI/ML systems including appropriate Bills of Materials (BOMs).
• Create security management strategies for safeguarding AI components during implementation and production.
• Synthesize DevSecOps principles with AI/ML-specific security requirements to develop comprehensive MLSecOps and AISecOps frameworks.