PPD: Permutation Phase Defense Against Adversarial Examples in Deep Learning

Authors: Mehdi Jafarnia-Jahromi, Tasmin Chowdhury, Hsin-Tai Wu, Sayandev Mukherjee
Published: 2018-12-25 | Updated: 2020-01-04

Source: https://arxiv.org/abs/1812.10049

PDF: https://arxiv.org/pdf/1812.10049

Labels Predicted by AI

敵対的学習 ロバスト性 敵対的サンプルの検知

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Deep neural networks have demonstrated cutting edge performance on various tasks including classification. However, it is well known that adversarially designed imperceptible perturbation of the input can mislead advanced classifiers. In this paper, Permutation Phase Defense (PPD), is proposed as a novel method to resist adversarial attacks. PPD combines random permutation of the image with phase component of its Fourier transform. The basic idea behind this approach is to turn adversarial defense problems analogously into symmetric cryptography, which relies solely on safekeeping of the keys for security. In PPD, safe keeping of the selected permutation ensures effectiveness against adversarial attacks. Testing PPD on MNIST and CIFAR-10 datasets yielded state-of-the-art robustness against the most powerful adversarial attacks currently available.