13/04/2021

Robust and private learning of halfspaces

Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thao Nguyen

Keywords:

Abstract Paper Similar Papers

Abstract: In this work, we study the trade-off between differential privacy and adversarial robustness under L_2-perturbations in the context of learning halfspaces. We prove nearly tight bounds on the sample complexity of robust private learning of halfspaces for a large regime of parameters. A highlight of our results is that robust and private learning is harder than robust or private learning alone. We complement our theoretical analysis with experimental results on the MNIST and USPS datasets, for a learning algorithm that is both differentially private and adversarially robust.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AISTATS 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 13:08 
 0
 0
 0
 1
 12:41 
 0
 0
 0
 0
 15:16 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 2:47 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 16:04 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 14:17 
 0
 0
 0
 0
 2:45 
 0
 0
 0
 0
 12:39 
 0
 0
 0
 0
 15:03 
 0
 0
 0
 0
 15:37 
 0
 0
 0
 0
 11:50 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 1
 15:50 
 0
 0
 0
 0
 15:54 
 0
 0
 0
 0
 3:08 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 20:02 
 0
 0
 0
 0
 12:12 
 0
 0
 0
 0
 14:39 
 0
 0
 0
 0
 2:43 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 18:09 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 13:44 
 0
 0
 0
 0
 12:27 
 0
 0
 0
 0
 12:45 
 0
 0
 0
 0
 19:03 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 15:44 
 0
 0
 0
 0
 5:14