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

arXiv: https://arxiv.org/abs/2203.10930 · HTML: https://mlsanity.com/paper/2203.10930/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 15 of 15)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses](https://mlsanity.com/paper/2005.06149/) (2020)
- [DARTS: Deceiving Autonomous Cars with Toxic Signs](https://mlsanity.com/paper/1802.06430/) (2018)
- [PuVAE: A Variational Autoencoder to Purify Adversarial Examples](https://mlsanity.com/paper/1903.00585/) (2019)
- [Adversarial Attack and Defense of Structured Prediction Models](https://mlsanity.com/paper/2010.01610/) (2020)
- [Encryption Inspired Adversarial Defense for Visual Classification](https://mlsanity.com/paper/2005.07998/) (2020)
- [Adversarial Defense based on Structure-to-Signal Autoencoders](https://mlsanity.com/paper/1803.07994/) (2018)
- [Adversarial Machine Learning based Partial-model Attack in IoT](https://mlsanity.com/paper/2006.14146/) (2020)
- [Adversarial Attacks on Convolutional Neural Networks in Facial Recognition Domain](https://mlsanity.com/paper/2001.11137/) (2020)
- [Block Switching: A Stochastic Approach for Deep Learning Security](https://mlsanity.com/paper/2002.07920/) (2020)

## Built on by (most cited first, 3 of 3)

- [Exploring Adversarial Attacks on Neural Networks: An Explainable Approach](https://mlsanity.com/paper/2303.06032/) (2023)
- [NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attacks](https://mlsanity.com/paper/2303.06151/) (2023)
- [GrabDAE: An Innovative Framework for Unsupervised Domain Adaptation Utilizing Grab-Mask and Denoise Auto-Encoder](https://mlsanity.com/paper/2410.08023/) (2024)

## Abstract (arXiv)

According to recent studies, the vulnerability of state-of-the-art Neural Networks to adversarial input samples has increased drastically. A neural network is an intermediate path or technique by which a computer learns to perform tasks using Machine learning algorithms. Machine Learning and Artificial Intelligence model has become a fundamental aspect of life, such as self-driving cars [1], smart home devices, so any vulnerability is a significant concern. The smallest input deviations can fool these extremely literal systems and deceive their users as well as administrator into precarious situations. This article proposes a defense algorithm that utilizes the combination of an auto-encoder [3] and block-switching architecture. Auto-coder is intended to remove any perturbations found in input images whereas the block switching method is used to make it more robust against White-box attacks. The attack is planned using FGSM [9] model, and the subsequent counter-attack by the proposed architecture will take place thereby demonstrating the feasibility and security delivered by the algorithm.