Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Defending DNN Adversarial Attacks with Pruning and Logits Augmentation

Abstract: 

Deep neural networks (DNNs) have been shown to be powerful models and perform extremely well on many complicated artificial intelligent tasks. However, recent research found that these powerful models are vulnerable to adversarial attacks, i.e., intentionally added imperceptible perturbations to DNN inputs can easily mislead the DNNs with extremely high confidence. In this work, we enhance the robustness of DNNs under adversarial attacks by using pruning method and logits augmentation, we achieve both effective defense against adversarial examples and DNN model compression. We have observed defense against adversarial attacks under the white box attack assumption. Our defense mechanisms work even better under the grey box attack assumption.

up
0 users have voted:

Paper Details

Authors:
Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin
Submitted On:
24 November 2018 - 8:54am
Short Link:
Type:
Presentation Slides
Event:
Paper Code:
1228
Document Year:
2018
Cite

Document Files

GlobalSip_Final.pdf

(426 downloads)

Subscribe

[1] Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin, "Defending DNN Adversarial Attacks with Pruning and Logits Augmentation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3769. Accessed: Dec. 13, 2018.
@article{3769-18,
url = {http://sigport.org/3769},
author = {Xiao Wang; Shaokai Ye; Pu Zhao; Xue Lin },
publisher = {IEEE SigPort},
title = {Defending DNN Adversarial Attacks with Pruning and Logits Augmentation},
year = {2018} }
TY - EJOUR
T1 - Defending DNN Adversarial Attacks with Pruning and Logits Augmentation
AU - Xiao Wang; Shaokai Ye; Pu Zhao; Xue Lin
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3769
ER -
Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. (2018). Defending DNN Adversarial Attacks with Pruning and Logits Augmentation. IEEE SigPort. http://sigport.org/3769
Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin, 2018. Defending DNN Adversarial Attacks with Pruning and Logits Augmentation. Available at: http://sigport.org/3769.
Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. (2018). "Defending DNN Adversarial Attacks with Pruning and Logits Augmentation." Web.
1. Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. Defending DNN Adversarial Attacks with Pruning and Logits Augmentation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3769