Back to the Drawing Board - A Critical Evaluation of Poisoning Attacks on Federated Learning

Back to the Drawing Board - A Critical Evaluation of Poisoning Attacks on Federated Learning

IEEE Symposium on Security and Privacy via YouTube Direct link

Introduction

1 of 23

1 of 23

Introduction

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Back to the Drawing Board - A Critical Evaluation of Poisoning Attacks on Federated Learning

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

  1. 1 Introduction
  2. 2 Traditional Machine Learning
  3. 3 CrossDevice FL
  4. 4 Poisoning Attacks
  5. 5 Literature
  6. 6 Key Question
  7. 7 Outline
  8. 8 Prior Work
  9. 9 Three Main Dimensions
  10. 10 Global Model Parameters
  11. 11 Model Poisoning
  12. 12 Takeaways
  13. 13 Impractical Threat Models
  14. 14 Most Severe Threat Model
  15. 15 Untargeted Attacks
  16. 16 Practical Threat Models
  17. 17 Intuition
  18. 18 Data Poisoning
  19. 19 Key Results
  20. 20 Nonrobust Federated Learning
  21. 21 Cross Silo Federated Learning
  22. 22 CrossDevice Federated Learning
  23. 23 Robustness of Federated Learning

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.