# Adversarial Examples Detection and Analysis with Layer-wise Autoencoders

arXiv: https://arxiv.org/abs/2006.10013 · HTML: https://mlsanity.com/paper/2006.10013/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [Visual Prompting for Adversarial Robustness](https://mlsanity.com/paper/2210.06284/) (2022)
- [iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection](https://mlsanity.com/paper/2201.02331/) (2022)
- [Reverse Engineering of Imperceptible Adversarial Image Perturbations](https://mlsanity.com/paper/2203.14145/) (2022)
- [Self-Supervised Adversarial Example Detection by Disentangled Representation](https://mlsanity.com/paper/2105.03689/) (2021)
- [Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs](https://mlsanity.com/paper/2501.16534/) (2025)
- [Dual Graphs of Polyhedral Decompositions for the Detection of Adversarial Attacks](https://mlsanity.com/paper/2211.13305/) (2022)
- [Can Adversarial Examples Be Parsed to Reveal Victim Model Information?](https://mlsanity.com/paper/2303.07474/) (2023)
- [Measuring the Contribution of Multiple Model Representations in Detecting Adversarial Instances](https://mlsanity.com/paper/2111.07035/) (2021)
- [Adversarial Detection with a Dynamically Stable System](https://mlsanity.com/paper/2411.06666/) (2024)

## Abstract (arXiv)

We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network. For this purpose, we train individual autoencoders at intermediate layers of the target network. This allows us to describe the manifold of true data and, in consequence, decide whether a given example has the same characteristics as true data. It also gives us insight into the behavior of adversarial examples and their flow through the layers of a deep neural network. Experimental results show that our method outperforms the state of the art in supervised and unsupervised settings.