Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN

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.

17 pages, 7 figures, uses simpleConference.sty

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• A study of the effect of JPG compression on adversarial images
• Houdini: Fooling Deep Structured Prediction Models
• MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples