paper-with-me

Papers

MAD-VAE: Manifold Awareness Defense Variational Autoencoder

2020-10-31 · Frederick Morlock, Dingsu Wang

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.

📄 PDF Abstract BibTeX arXiv:2011.01755

Code (1)

Derek-Wds/MAD-VAE 공식 구현 pytorch

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Adversarial Purification with the Manifold Hypothesis

2022-10-26 · Zhaoyuan Yang, Zhiwei Xu, Jing Zhang, Richard Hartley 외

In this work, we formulate a novel framework for adversarial robustness using the manifold hypothesis. This framework provides sufficient conditions for defending against adversarial examples. We develop an adversarial p…

Adversarial PurificationAdversarial RobustnessVariational Inference

Manifold Projection for Adversarial Defense on Face Recognition

2020-08-01 · ECCV 2020 8 · Jianli Zhou, Chao Liang, Jun Chen

Although deep convolutional neural network based face recognition system has achieved remarkable success, it is susceptible to adversarial images: carefully constructed imperceptible perturbations can easily mislead deep…

Adversarial DefenseFace Recognition

PuVAE: A Variational Autoencoder to Purify Adversarial Examples

2019-03-02 · Uiwon Hwang, Jaewoo Park, Hyemi Jang, Sungroh Yoon 외

Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed…

Adversarial DefenseAdversarial Defense against FGSM Attack

Diffusion Variational Autoencoders

2019-01-25 · Luis A. Pérez Rey, Vlado Menkovski, Jacobus W. Portegies

A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational…

Variational Autoencoder with Learned Latent Structure

2020-06-18 · Marissa C. Connor, Gregory H. Canal, Christopher J. Rozell

The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this manifold by learning mappings from low-…