APE-GAN: Adversarial Perturbation Elimination with GAN
Although neural networks could achieve state-of-the-art performance while recongnizing images, they often suffer a tremendous defeat from adversarial examples--inputs generated by utilizing imperceptible but intentional perturbation to clean samples from the datasets. How to defense against adversarial examples is an important problem which is well worth researching. So far, very few methods have provided a significant defense to adversarial examples. In this paper, a novel idea is proposed and an effective framework based Generative Adversarial Nets named APE-GAN is implemented to defense against the adversarial examples. The experimental results on three benchmark datasets including MNIST, CIFAR10 and ImageNet indicate that APE-GAN is effective to resist adversarial examples generated from five attacks.
Code (3)
Similar Papers 제목 키워드 기반
MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination
Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absen…
Image ClassificationBoosting the Transferability of Adversarial Attacks with Global Momentum Initialization
Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across …
A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits
We consider the sequential optimization of an unknown, continuous, and expensive to evaluate reward function, from noisy and adversarially corrupted observed rewards. When the corruption attacks are subject to a suitable…
Adversarial Training: embedding adversarial perturbations into the parameter space of a neural network to build a robust system
Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in…
DiversityRobust Weight Perturbation for Adversarial Training
Overfitting widely exists in adversarial robust training of deep networks. An effective remedy is adversarial weight perturbation, which injects the worst-case weight perturbation during network training by maximizing th…
Classification