PDA: Progressive Data Augmentation for General Robustness of Deep Neural Networks

Authors: Hang Yu, Aishan Liu, Xianglong Liu, Gengchao Li, Ping Luo, Ran Cheng, Jichen Yang, Chongzhi Zhang
Published: 2019-09-11 | Updated: 2020-02-24

Source: https://arxiv.org/abs/1909.04839

PDF: https://arxiv.org/pdf/1909.04839

Labels Predicted by AI

ポイズニング 攻撃手法 モデルの堅牢性

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

Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustness against adversarial samples, most of them fail to improve the robustness on common corruptions such as noise, blur, and weather/digital effects (e.g. frost, pixelate). To address this problem, we propose a simple yet effective method, named Progressive Data Augmentation (PDA), which enables general robustness of DNNs by progressively injecting diverse adversarial noises during training. In other words, DNNs trained with PDA are able to obtain more robustness against both adversarial attacks as well as common corruptions than the recent state-of-the-art methods. We also find that PDA is more efficient than prior arts and able to prevent accuracy drop on clean samples without being attacked. Furthermore, we theoretically show that PDA can control the perturbation bound and guarantee better generalization ability than existing work. Extensive experiments on many benchmarks such as CIFAR-10, SVHN, and ImageNet demonstrate that PDA significantly outperforms its counterparts in various experimental setups.