AI Product Security: Secure Architecture, Deployment, and Infrastructure

In this course, Sam Sehgal—a cloud and application security leader—provides a thorough guide to building secure AI products, focusing on the unique security challenges in machine learning (ML) and large language models (LLMs). Learn how to safeguard AI systems across all stages of development, from data protection and secure coding to model and deployment security. Explore essential security frameworks, threat modeling, and mitigation strategies that can help you anticipate and defend against potential attacks. Dive into industry best practices for securing AI deployments, infrastructure, and the software supply chain. By the end of the course, you'll be equipped to apply logging, monitoring, and auditing techniques to maintain ongoing system security and compliance. Whether you're a developer, product manager, or security professional, this course prepares you with the skills to secure your AI products end-to-end.

Learning objectives
Identify the key security threats and vulnerabilities specific to machine learning (ML) and large language model (LLM)-based AI products.
Explain the end-to-end architecture of AI systems and the security measures required at each stage of development, deployment, and operation.
Apply best practices for securing data, code, and models in AI products to prevent breaches, adversarial attacks, and unauthorized access.
Evaluate different security frameworks and techniques for protecting AI deployments and infrastructure, ensuring robust protection in production environments.