02/02/2021

Adversarial Defence by Diversified Simultaneous Training of Deep Ensembles

Bo Huang, Zhiwei Ke, Yi Wang, Wei Wang, Linlin Shen, Feng Liu

Keywords:

Abstract Paper Similar Papers

Abstract: Learning-based classifiers are susceptible to adversarial examples. Existing defence methods are mostly devised on individual classifiers. Recent studies showed that it is viable to increase adversarial robustness by promoting diversity over an ensemble of models. In this paper, we propose adversarial defence by encouraging ensemble diversity on learning high-level feature representations and gradient dispersion in simultaneous training of deep ensemble networks. We perform extensive evaluations under white-box and black-box attacks including transferred examples and adaptive attacks. Our approach achieves a significant gain of up to 52% in adversarial robustness, compared with the baseline and the state-of-the-art method on image benchmarks with complex data scenes. The proposed approach complements the defence paradigm of adversarial training, and can further boost the performance. The source code is available at https://github.com/ALIS-Lab/AAAI2021-PDD.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948849
(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
 1:01 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 9:30 
 0
 0
 0
 1
 4:31 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 14:30 
 0
 0
 0
 0
 3:59 
 0
 0
 0
 0
 4:33 
 0
 0
 0
 0
 11:06 
 0
 0
 0
 0
 14:34 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 5:23 
 0
 1
 0
 0
 5:01 
 0
 0
 0
 0
 9:00 
 0
 0
 0
 0
 17:30 
 0
 0
 0
 0
 3:39 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 11:32 
 0
 0
 0
 0
 2:42 
 0
 0
 0
 0
 14:15 
 0
 0
 0
 0
 15:35 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 14:39 
 0
 0
 0
 0
 16:06 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 0:56 
 0
 0
 0
 0
 2:58 
 0
 0
 0
 0
 4:33 
 0
 0
 0
 0
 3:59 
 0
 0
 0
 0
 9:28 
 0
 0
 0
 0
 10:18 
 0
 0
 0
 0
 14:07 
 0
 0
 0
 0
 6:06 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 11:41 
 0
 0
 0
 0
 13:56 
 0
 0
 0
 0
 14:15 
 0
 0
 0
 0
 14:52