# Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN

Source: [Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN](<https://www.sota2.com/research/paper/68fa69701e209131cea22112>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:06:39.448Z

Authors: Desheng Wang, Weidong Jin, Yunpu Wu, Aamir Khan (1) \_\_INSTITUTION\_4\_\_ School of Electrical Engineering, Southwest Jiaotong University, Chengdu, P. R. China)

Published: 2021-03-08T02:18:24.000Z

## Abstract

Convolutional neural networks (CNNs) have achieved beyond human-level accuracy in the image classification task and are widely deployed in real-world environments. However, CNNs show vulnerability to adversarial perturbations that are well-designed noises aiming to mislead the classification models. In order to defend against the adversarial perturbations, adversarially trained GAN (ATGAN) is proposed to improve the adversarial robustness generalization of the state-of-the-art CNNs trained by adversarial training. ATGAN incorporates adversarial training into standard GAN training procedure to remove obfuscated gradients which can lead to a false sense in defending against the adversarial perturbations and are commonly observed in existing GANs-based adversarial defense methods. Moreover, ATGAN adopts the image-to-image generator as data augmentation to increase the sample complexity needed for adversarial robustness generalization in adversarial training. Experimental results in MNIST SVHN and CIFAR-10 datasets show that the proposed method doesn't rely on obfuscated gradients and achieves better global adversarial robustness generalization performance than the adversarially trained state-of-the-art CNNs.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.04513>)

[PDF](<https://arxiv.org/pdf/2103.04513.pdf>)
