# Combatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approach

arXiv: https://arxiv.org/abs/1812.03087 · HTML: https://mlsanity.com/paper/1812.03087/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2018.

## Built on by (most cited first, 10 of 10)

- [Projected Randomized Smoothing for Certified Adversarial Robustness](https://mlsanity.com/paper/2309.13794/) (2023)
- [Frequency Centric Defense Mechanisms against Adversarial Examples](https://mlsanity.com/paper/2110.13935/) (2021)
- [Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework](https://mlsanity.com/paper/2202.02626/) (2022)
- [Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problem](https://mlsanity.com/paper/2202.08944/) (2022)
- [A deep learning model for burn depth classification using ultrasound imaging](https://mlsanity.com/paper/2203.15879/) (2022)
- [Mitigating Gradient-based Adversarial Attacks via Denoising and Compression](https://mlsanity.com/paper/2104.01494/) (2021)
- [Topological safeguard for evasion attack interpreting the neural networks' behavior](https://mlsanity.com/paper/2402.07480/) (2024)
- [Understanding Deep Learning defenses Against Adversarial Examples Through Visualizations for Dynamic Risk Assessment](https://mlsanity.com/paper/2402.07496/) (2024)
- [How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?](https://mlsanity.com/paper/2504.10850/) (2025)
- [A look at adversarial attacks on radio waveforms from discrete latent space](https://mlsanity.com/paper/2506.09896/) (2025)

## Abstract (arXiv)

Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based attacks: The Fast Gradient Sign attack and Fast Gradient attack. First we use an autoencoder to denoise the test data, which is trained with both clean and corrupted data. Then, we reduce the dimension of the denoised data using the hidden layer representation of another autoencoder. We perform this experiment for multiple values of the bound of adversarial perturbations, and consider different numbers of reduced dimensions. When the test data is preprocessed using this cascaded pipeline, the tested deep neural network classifier yields a much higher accuracy, thus mitigating the effect of the adversarial perturbation.