Completed
Security and ML inference
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
BlindAI: Secure Remote ML Inference with Intel SGX Enclaves
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Security and ML inference
- 3 On-device Machine Learning
- 4 Homomorphic encryption
- 5 Confidential Computing
- 6 Trusted computing base
- 7 Shrink the TCB
- 8 Overview
- 9 Enclave manifest
- 10 Threat: Memory vulnerability
- 11 Defense: SGX enclave in Rust
- 12 Threat: lago attacks, Confused dep
- 13 Threat: Software side channels
- 14 Defense : Constant-time programming
- 15 Side channel mitigation for the application code Hard to enforce in all code: ⚫ Compiler are allowed to add "side channel" when optimizing
- 16 Threat: n-day attacks
- 17 Defense: Plan for the worst
- 18 Transparency: reproducibility
- 19 Transparency: optimize for auditability
- 20 How do we protect ourselves?
