Adversary Instantiation - Lower Bounds for Differentially Private Machine Learning

Adversary Instantiation - Lower Bounds for Differentially Private Machine Learning

IEEE Symposium on Security and Privacy via YouTube Direct link

We want to calculate the epsilon.

4 of 10

4 of 10

We want to calculate the epsilon.

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Adversary Instantiation - Lower Bounds for Differentially Private Machine Learning

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

  1. 1 Intro
  2. 2 Machine Learning Is Not Private
  3. 3 Machine learning with Differential Privacy
  4. 4 We want to calculate the epsilon.
  5. 5 We Focus on DPSGD!
  6. 6 Membership inference
  7. 7 Worst-Case Example
  8. 8 Intermediate Model Access
  9. 9 Adaptive Intermediate Model Acce Distinguisher
  10. 10 Gradient Poisoning Attack

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.