MAD-VAE: Manifold Awareness Defense Variational Autoencoder

Abstract

Although deep generative models such as Defense-GAN and Defense-VAE have made significant progress in terms of adversarial defenses of image classification neural networks, several methods have been found to circumvent these defenses. Based on Defense-VAE, in our research we introduce several methods to improve the robustness of defense models. The methods introduced in this paper are straight forward yet show promise over the vanilla Defense-VAE. With extensive experiments on MNIST data set, we have demonstrated the effectiveness of our algorithms against different attacks. Our experiments also include attacks on the latent space of the defensive model. We also discuss the applicability of existing adversarial latent space attacks as they may have a significant flaw.

arXiv comment15 pages, 13 figures

References in corpus (12)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Auto-Encoding Variational Bayes
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• On the (Statistical) Detection of Adversarial Examples
• Simple Black-Box Adversarial Perturbations for Deep Networks
• Simple Black-box Adversarial Attacks
• Towards Deeper Understanding of Variational Autoencoding Models
• The Robust Manifold Defense: Adversarial Training using Generative Models
• On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
• Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks