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

Defending DNN Adversarial Attacks with Pruning and Logits Augmentation

Citation Author(s):
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin
Submitted by:
Siyue Wang
Last updated:
28 November 2018 - 8:40pm
Document Type:
Presentation Slides
Document Year:
Pu Zhao
Paper Code:


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 ofDNNs 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.

0 users have voted: