Corrupting data to remove deceptive perturbation: using preprocessing method to improve system robustness
Files
Published version
Date
DOI
Authors
Chin, Sang
Le, Hieu
Tran, Dung
Walker, Hans
Version
Published version
OA Version
Citation
S. Chin, H. Le, D. Tran, H. Walker. "Corrupting Data to Remove Deceptive Perturbation: Using Preprocessing Method to Improve System Robustness." International Conference on Computational Science and Computational Intelligence, 2021
Abstract
Although deep neural networks have achieved great
performance on classification tasks, recent studies showed that
well trained networks can be fooled by adding subtle noises. This
paper introduces a new approach to improve neural network
robustness by applying the recovery process on top of the
naturally trained classifier. In this approach, images will be
intentionally corrupted by some significant operator and then be
recovered before passing through the classifiers. SARGAN - an
extension on Generative Adversarial Networks (GAN) is capable
of denoising radar signals. This paper will show that SARGAN
can also recover corrupted images by removing the adversarial
effects. Our results show that this approach does improve the
performance of naturally trained networks.
Description
License
Add dc.rights: This version of the work is distributed under a Creative Commons Attribution 4.0 International license.