Log In Sign Up

HAD-GAN: A Human-perception Auxiliary Defense GAN model to Defend Adversarial Examples

by   Wanting Yu, et al.

Adversarial examples reveal the vulnerability and unexplained nature of neural networks. It is of great practical significance to study the defense of adversarial examples. In fact, most adversarial examples that misclassify networks are often undetectable by humans. In this paper, we propose a defense model to train the classifier into a human-perception classification model with shape preference. The proposed model consisting of a TTN (Texture Transfer Network) and an auxiliary defense GAN (Generative Adversarial Networks) is called HAD-GAN (Human-perception Auxiliary Defense GAN). The TTN is used to extend the texture samples of a clean image and makes classifiers more focused on its shape. And GAN is utilized to form a training framework for the model and generate the images we need. A series of experiments conducted on MNIST, Fashion-MNIST and CIFAR10 show that the proposed model outperforms the state-of-the-art defense methods for network robust, and have a significant improvement on defense ability of adversarial examples.


page 7

page 10

page 11

page 12

page 19

page 20


APE-GAN: Adversarial Perturbation Elimination with GAN

Although neural networks could achieve state-of-the-art performance whil...

Generative Adversarial Examples

Adversarial examples are typically constructed by perturbing an existing...

AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense

We propose an AID-purifier that can boost the robustness of adversariall...

Improved Network Robustness with Adversary Critic

Ideally, what confuses neural network should be confusing to humans. How...

VectorDefense: Vectorization as a Defense to Adversarial Examples

Training deep neural networks on images represented as grids of pixels h...

Salient Feature Extractor for Adversarial Defense on Deep Neural Networks

Recent years have witnessed unprecedented success achieved by deep learn...

Training Robust Deep Neural Networks via Adversarial Noise Propagation

Deep neural networks have been found vulnerable to noises like adversari...