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