AI Chat AI Image Generator AI Video Text to Speech

Adversarial Defense of Image Classification Using a Variational Auto-Encoder

12/07/2018

∙

by Yi Luo, et al.

∙

∙

Deep neural networks are known to be vulnerable to adversarial attacks. This exposes them to potential exploits in security-sensitive applications and highlights their lack of robustness. This paper uses a variational auto-encoder (VAE) to defend against adversarial attacks for image classification tasks. This VAE defense has a few nice properties: (1) it is quite flexible and its use of randomness makes it harder to attack; (2) it can learn disentangled representations that prevent blurry reconstruction; and (3) a patch-wise VAE defense strategy is used that does not require retraining for different size images. For moderate to severe attacks, this system outperforms or closely matches the performance of JPEG compression, with the best quality parameter. It also has more flexibility and potential for improvement via training.

Yi Luo
60 publications
Henry Pfister
3 publications

research

∙ 11/05/2018

FUNN: Flexible Unsupervised Neural Network

Deep neural networks have demonstrated high accuracy in image classifica...

0 David Vigouroux, et al. ∙

research

∙ 03/11/2022

An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks

According to recent studies, the vulnerability of state-of-the-art Neura...

0 Anirudh Yadav, et al. ∙

research

∙ 12/17/2018

Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks

Deep neural networks (DNNs) have been enormously successful across a var...

0 Xiang Li, et al. ∙

research

∙ 03/10/2021

Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks

In this work, we explore adversarial attacks on the Variational Autoenco...

0 Anna Kuzina, et al. ∙

research

∙ 03/11/2022

Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification

Adversarial attacks are often considered as threats to the robustness of...

2 Jianzhang Zheng, et al. ∙

research

∙ 02/25/2023

Chaotic Variational Auto encoder-based Adversarial Machine Learning

Machine Learning (ML) has become the new contrivance in almost every fie...

0 Pavan Venkata Sainadh Reddy, et al. ∙

research

∙ 06/20/2023

Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data

The ability of deep learning (DL) approaches to learn generalised signal...

0 Shreejit Jadhav, et al. ∙