1. Data Protection States and the In-Use Gap
4 lessonsUnderstand why traditional encryption at rest and in transit leaves data vulnerable during processing, and how confidential computing addresses this gap.
2. Trusted Execution Environments and Hardware Primitives
5 lessonsLearn how TEEs isolate workloads using hardware-enforced memory encryption and access controls across different processor architectures.
3. Remote Attestation and Cryptographic Verification
5 lessonsImplement attestation protocols that let clients verify workload integrity before releasing sensitive data to protected environments.
4. Securing RAG Systems and Vector Databases
5 lessonsDesign retrieval-augmented generation pipelines that protect confidential documents and embeddings during indexing, search, and context assembly.
5. Confidential Inference and Model Serving
4 lessonsDeploy inference workloads that protect model weights, input prompts, and intermediate activations from infrastructure operators and co-tenants.
6. Fine-Tuning and Training with Sensitive Data
5 lessonsArchitect training and fine-tuning pipelines that keep proprietary datasets and updated model parameters inside protected memory.
7. Defense in Depth and Operational Hardening
6 lessonsCombine confidential computing with application security, side-channel mitigations, and supply chain controls for robust AI system protection.
Get an email when this course opens