Adversarial Defense by Suppressing High-frequency Components

Code

• github.com/zzd1992/Adversarial-Defense-by-Suppressing-High-Frequencies
  OfficialIn paperpytorch★ 0

Abstract

Recent works show that deep neural networks trained on image classification dataset bias towards textures. Those models are easily fooled by applying small high-frequency perturbations to clean images. In this paper, we learn robust image classification models by removing high-frequency components. Specifically, we develop a differentiable high-frequency suppression module based on discrete Fourier transform (DFT). Combining with adversarial training, we won the 5th place in the IJCAI-2019 Alibaba Adversarial AI Challenge. Our code is available online.

Tasks

Reproductions