The Advent of Confidential AI

Raghu Yeluri

[un]prompted 2026 — AI Security Practitioner Conference · Day 1 · 2

AI models and training data are exposed to cloud administrators, rogue insiders, and co-tenants in ways that most practitioners don't fully account for. Intel's Raghu Yeluri presents Confidential AI — hardware-enforced Trusted Execution Environments that encrypt AI workloads even from the cloud provider itself — and walks through three concrete deployments, including multi-hospital federated learning that complies with HIPAA without any party ever seeing another's data. ---

AI review

Intel employee delivers competent Intel product pitch wrapped in legitimate threat framing. The multi-hospital federated learning example is the strongest material — a real compliance problem with a real solution. But this is fundamentally a TDX availability announcement dressed as a security talk.