Protecting the Protector - Hardening Machine Learning Defenses Against Adversarial Attacks

Protecting the Protector - Hardening Machine Learning Defenses Against Adversarial Attacks

Black Hat via YouTube Direct link

Intro

1 of 27

1 of 27

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Protecting the Protector - Hardening Machine Learning Defenses Against Adversarial Attacks

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Windows Defender Advanced Threat Protection
  3. 3 Windows Defender ATP Research
  4. 4 Types of Machine Learning
  5. 5 Machine Learning for Endpoint Protection
  6. 6 Client Machine Learning
  7. 7 Cloud Machine Learning
  8. 8 Theoretical Attack Vectors: Supervised Model
  9. 9 Attacks on Certificate Reputation (Early 2017)
  10. 10 Attacks on Certificate Reputation (cont.)
  11. 11 Challenges
  12. 12 Diverse Models 1. Different feature sets
  13. 13 Features - Highly dimensional data
  14. 14 Diverse Set of Classifiers Feature Set PE Properties
  15. 15 Optimizing for Different Threat Scenarios
  16. 16 Boolean Stacking TRAINING DATA
  17. 17 Model Selection
  18. 18 Data Leaks
  19. 19 Using Unsupervised Features
  20. 20 Experiment Design Supervised Training
  21. 21 What if ... Attacker crafts adversarial samples to flip verdicts SAMPLES
  22. 22 Realtime Monitoring
  23. 23 Impact of Ensemble Models
  24. 24 Bonus: Interpretability
  25. 25 Benefits of an Ensemble Model
  26. 26 Recent Realworld Case Studies (2)
  27. 27 Key Takeaways

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.