BlindAI: Secure Remote ML Inference with Intel SGX Enclaves

BlindAI: Secure Remote ML Inference with Intel SGX Enclaves

Confidential Computing Consortium via YouTube Direct link

Overview

8 of 20

8 of 20

Overview

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

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.