The Devil is in the GAN - Defending Deep Generative Models Against Adversarial Attacks

The Devil is in the GAN - Defending Deep Generative Models Against Adversarial Attacks

Black Hat via YouTube Direct link

Approach trail

12 of 20

12 of 20

Approach trail

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

The Devil is in the GAN - Defending Deep Generative Models Against Adversarial Attacks

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

  1. 1 Introduction
  2. 2 Research Goals
  3. 3 What are Deep Generative Models
  4. 4 Applications of Deep Generative Models
  5. 5 What Could Go Wrong
  6. 6 What Makes a Successful Attack
  7. 7 Model Inspection
  8. 8 Brute Force Sampling
  9. 9 mnist
  10. 10 Training
  11. 11 Can you do something better
  12. 12 Approach trail
  13. 13 Approach schematic
  14. 14 Student Model
  15. 15 Redundancy
  16. 16 Token Example
  17. 17 Stylegun
  18. 18 Attack Goals
  19. 19 Basic Defenses
  20. 20 Whitebox Access

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.