APE-GAN: Adversarial Perturbation Elimination with GAN

Abstract

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.

arXiv comment14 pages

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Distilling the Knowledge in a Neural Network
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Residual Learning for Image Recognition
• Densely Connected Convolutional Networks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• DeepFool: a simple and accurate method to fool deep neural networks
• Practical Black-Box Attacks against Machine Learning
• Extending Defensive Distillation
• The Limitations of Deep Learning in Adversarial Settings

Cited by in corpus (22)

• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective
• MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
• Towards quantum enhanced adversarial robustness in machine learning
• Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics
• Generative Adversarial Networks: A Survey Towards Private and Secure Applications
• Improving adversarial robustness of deep neural networks by using semantic information
• Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
• Adversarial Sampling for Fairness Testing in Deep Neural Network
• CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification
• Unrestricted Adversarial Attacks on ImageNet Competition
• A Self-supervised Approach for Adversarial Robustness
• Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders
• Minimax Defense against Gradient-based Adversarial Attacks
• Ensembling with Deep Generative Views
• Local Competition and Stochasticity for Adversarial Robustness in Deep Learning
• Unifying Bilateral Filtering and Adversarial Training for Robust Neural Networks
• Local Competition and Uncertainty for Adversarial Robustness in Deep Learning
• Orthogonal Deep Models As Defense Against Black-Box Attacks
• Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks
• FUNN: Flexible Unsupervised Neural Network