# Towards Adversarial Purification using Denoising AutoEncoders

arXiv: https://arxiv.org/abs/2208.13838 · HTML: https://mlsanity.com/paper/2208.13838/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 29 Aug 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [MagNet: a Two-Pronged Defense against Adversarial Examples](https://mlsanity.com/paper/1705.09064/) (2017)
- [Detecting Adversarial Samples from Artifacts](https://mlsanity.com/paper/1703.00410/) (2017)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses](https://mlsanity.com/paper/2005.06149/) (2020)
- [Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics](https://mlsanity.com/paper/1612.07767/) (2016)
- [Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy](https://mlsanity.com/paper/1906.06784/) (2019)
- [Maximum Mean Discrepancy Test is Aware of Adversarial Attacks](https://mlsanity.com/paper/2010.11415/) (2020)
- [Early Methods for Detecting Adversarial Images](https://mlsanity.com/paper/1608.00530/) (2016)
- [DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation](https://mlsanity.com/paper/1908.05195/) (2019)
- [SAD: Saliency-based Defenses Against Adversarial Examples](https://mlsanity.com/paper/2003.04820/) (2020)

## Built on by (most cited first, 6 of 6)

- [Enhancing Adversarial Robustness via Score-Based Optimization](https://mlsanity.com/paper/2307.04333/) (2023)
- [Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness](https://mlsanity.com/paper/2310.18762/) (2023)
- [LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks](https://mlsanity.com/paper/2502.20562/) (2025)
- [VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systems](https://mlsanity.com/paper/2507.05146/) (2025)
- [NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations](https://mlsanity.com/paper/2510.14025/) (2025)
- [TopoReformer: Mitigating Adversarial Attacks Using Topological Purification in OCR Models](https://mlsanity.com/paper/2511.15807/) (2025)

## Abstract (arXiv)

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are primarily attributed from the purity of the training samples, therefore the deep learning architectures are often susceptible to adversarial attacks. Adversarial attacks are often obtained by making subtle perturbations to normal images, which are mostly imperceptible to humans, but can seriously confuse the state-of-the-art machine learning models. We propose a framework, named APuDAE, leveraging Denoising AutoEncoders (DAEs) to purify these samples by using them in an adaptive way and thus improve the classification accuracy of the target classifier networks that have been attacked. We also show how using DAEs adaptively instead of using them directly, improves classification accuracy further and is more robust to the possibility of designing adaptive attacks to fool them. We demonstrate our results over MNIST, CIFAR-10, ImageNet dataset and show how our framework (APuDAE) provides comparable and in most cases better performance to the baseline methods in purifying adversaries. We also design adaptive attack specifically designed to attack our purifying model and demonstrate how our defense is robust to that.