02/02/2021

Self-Progressing Robust Training

Minhao Cheng, Pin-Yu Chen, Sijia Liu, Shiyu Chang, Cho-Jui Hsieh, Payel Das

Keywords:

Abstract Paper Similar Papers

Abstract: Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods such as adversarial training explicitly uses an ``attack'' (e.g., l_infty-norm bounded perturbation) to generate adversarial examples during model training for improving adversarial robustness. In this paper, we take a different perspective and propose a new framework SPROUT, self-progressing robust training. During model training, SPROUT progressively adjusts training label distribution via our proposed parametrized label smoothing technique, making training free of attack generation and more scalable. We also motivate SPROUT using a general formulation based on vicinity risk minimization, which includes many robust training methods as special cases. Compared with state-of-the-art adversarial training methods (PGD-l_infty and TRADES) under l_infty-norm bounded attacks and various invariance tests, SPROUT consistently attains superior performance and is more scalable to large neural networks. Our results shed new light on scalable, effective and attack-independent robust training methods.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948652
(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
 7:36 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 13:39 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 12:04 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 15:58 
 0
 1
 0
 0
 5:06 
 0
 0
 0
 0
 11:27 
 0
 0
 0
 0
 3:59 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 1
 9:03 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 17:41 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 3:39 
 0
 0
 0
 0
 8:39 
 0
 0
 0
 0
 15:49 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 4:59 
 0
 1
 0
 0
 15:26 
 0
 0
 0
 0
 5:17 
 0
 0
 0
 1
 4:50 
 0
 0
 0
 0
 3:03 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 12:55 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 13:15 
 0
 0
 0
 0
 4:05 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 0:55 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 14:52