Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training

Authors: Alfred Laugros, Alice Caplier, Matthieu Ospici
Published: 2020-08-19

Source: https://arxiv.org/abs/2008.08384

PDF: https://arxiv.org/pdf/2008.08384

Labels Predicted by AI

敵対的サンプル 堅牢性向上手法 敵対的サンプルの脆弱性

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

Despite their performance, Artificial Neural Networks are not reliable enough for most of industrial applications. They are sensitive to noises, rotations, blurs and adversarial examples. There is a need to build defenses that protect against a wide range of perturbations, covering the most traditional common corruptions and adversarial examples. We propose a new data augmentation strategy called M-TLAT and designed to address robustness in a broad sense. Our approach combines the Mixup augmentation and a new adversarial training algorithm called Targeted Labeling Adversarial Training (TLAT). The idea of TLAT is to interpolate the target labels of adversarial examples with the ground-truth labels. We show that M-TLAT can increase the robustness of image classifiers towards nineteen common corruptions and five adversarial attacks, without reducing the accuracy on clean samples.