02/02/2021

Learning Model-Based Privacy Protection under Budget Constraints

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

Keywords:

Abstract Paper Similar Papers

Abstract: Protecting privacy in gradient-based learning has become increasingly critical as more sensitive information is being used. Many existing solutions seek to protect the sensitive gradients by constraining the overall privacy cost within a constant budget, where the protection is hand-designed and empirically calibrated to boost the utility of the resulting model. However, it remains challenging to choose the proper protection adapted for specific constraints so that the utility is maximized. To this end, we propose a novel Learning-to-Protect algorithm that automatically learns a model-based protector from a set of non-private learning tasks. The learned protector can be applied to private learning tasks to improve utility within the specific privacy budget constraint. Our empirical studies on both synthetic and real datasets demonstrate that the proposed algorithm can achieve a superior utility with a given privacy constraint and generalize well to new private datasets distributed differently as compared to the hand-designed competitors.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948883
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 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
 14:59 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 15:37 
 0
 0
 0
 0
 16:04 
 0
 0
 0
 0
 14:14 
 0
 0
 0
 0
 13:29 
 0
 0
 0
 0
 14:17 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 13:08 
 0
 0
 0
 0
 14:17 
 0
 0
 0
 0
 15:44 
 0
 0
 0
 0
 19:03 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 1
 15:50 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 14:29 
 0
 0
 0
 0
 15:38 
 0
 0
 0
 0
 8:17 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 13:44 
 0
 0
 0
 0
 9:36 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 17:18 
 0
 0
 0
 0
 17:14 
 0
 0
 0
 0
 14:03 
 0
 0
 0
 0
 13:55 
 0
 0
 0
 0
 18:15 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 14:54 
 0
 0
 0
 0
 12:45 
 0
 0
 0
 1
 12:41 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 25:00 
 0
 0
 0
 0
 15:10 
 0
 0
 0
 0
 12:27 
 0
 0
 0
 0
 8:15 
 0
 0
 0
 0
 14:47