# MAD-VAE: Manifold Awareness Defense Variational Autoencoder

Source: [MAD-VAE: Manifold Awareness Defense Variational Autoencoder](<https://www.sota2.com/research/paper/68fa68ab1e209131cea1da59>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:43:58.904Z

Authors: Frederick Morlock, Dingsu Wang

Published: 2020-10-31T09:04:25.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2011.01755>)

[PDF](<https://arxiv.org/pdf/2011.01755.pdf>)