02/02/2021

Tightening Robustness Verification of Convolutional Neural Networks with Fine-Grained Linear Approximation

Yiting Wu, Min Zhang

Keywords:

Abstract Paper Similar Papers

Abstract: The robustness of neural networks can be quantitatively indicated by a lower bound within which any perturbation does not alter the original input’s classification result. A certified lower bound is also a criterion to evaluate the performance of robustness verification approaches. In this paper, we present a tighter linear approximation approach for the robustness verification of Convolutional Neural Networks (CNNs). By the tighter approximation, we can tighten the robustness verification of CNNs, i.e., proving they are robust within a larger 10 perturbation distance. Furthermore, our approach is applicable to general sigmoid-like activation functions. We implement DeepCert, the resulting verification toolkit. We evaluate it with open-source benchmarks, including LeNet and the models trained on MNIST and CIFAR. Experimental results show that DeepCert outperforms other state-of-the-art robustness verification tools with at most 286.28% improvement to the certified lower bound and 1566.76 times speedup for the same neural networks.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949138
(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
 5:30 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 5:23 
 0
 0
 0
 0
 4:16 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 3:27 
 0
 0
 0
 0
 16:21 
 0
 0
 0
 0
 13:49 
 0
 0
 0
 1
 3:14 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 12:51 
 0
 0
 0
 0
 12:45 
 0
 0
 0
 0
 12:09 
 0
 0
 0
 0
 3:26 
 0
 0
 0
 0
 10:07 
 0
 0
 0
 0
 14:12 
 0
 0
 0
 0
 4:08 
 0
 0
 0
 0
 11:09 
 0
 0
 0
 0
 4:23 
 0
 0
 0
 0
 11:32 
 0
 0
 0
 0
 4:36 
 0
 0
 0
 0
 2:58 
 0
 0
 0
 0
 5:51 
 0
 0
 0
 0
 20:21 
 0
 0
 0
 0
 15:12 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 0:50 
 0
 0
 0
 0
 16:34 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 11:35 
 0
 0
 0
 0
 3:58