Zero Trust for AI: Applying Security Principles to AI Workloads
About this session
As AI systems rapidly move into production, traditional security models struggle to keep pace with dynamic, data-driven workloads. This session introduces a Zero Trust approach for AI, rethinking how identity, access, and trust boundaries apply to models, data pipelines, and autonomous agents. We will explore practical patterns to secure AI workloads—covering model access control, secure inference APIs, data isolation, and runtime monitoring. Attendees will learn how to apply Zero Trust principles such as least privilege, continuous verification, and segmentation to AI systems, enabling resilient, secure, and scalable deployments without slowing innovation.
Speaker
Key takeaways
- How to apply Zero Trust principles to AI systems: Understand how concepts like least privilege, identity-first security, and continuous verification translate to models, data pipelines, and AI agents.
- Design patterns for securing AI workloads in production: Learn practical approaches to protect model access, secure inference APIs, isolate sensitive data, and enforce runtime controls.
- How to mitigate emerging AI-specific security risks: Identify and defend against threats such as prompt injection, data leakage, model misuse, and unauthorized access in AI-driven applications.