# Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators

arXiv: https://arxiv.org/abs/2101.04645 · HTML: https://mlsanity.com/paper/2101.04645/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 12 Jan 2021.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Classification-Based Anomaly Detection for General Data](https://mlsanity.com/paper/2005.02359/) (2020)
- [MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks](https://mlsanity.com/paper/1901.04997/) (2019)
- [Deep Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/1911.08623/) (2019)
- [Seeing What a GAN Cannot Generate](https://mlsanity.com/paper/1910.11626/) (2019)
- [Adversarially Learned Anomaly Detection](https://mlsanity.com/paper/1812.02288/) (2018)
- [Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection](https://mlsanity.com/paper/1806.04808/) (2018)
- [Robust Anomaly Detection in Images using Adversarial Autoencoders](https://mlsanity.com/paper/1901.06355/) (2019)
- [DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN](https://mlsanity.com/paper/1808.07632/) (2018)
- [One-Class Adversarial Nets for Fraud Detection](https://mlsanity.com/paper/1803.01798/) (2018)
- [Fence GAN: Towards Better Anomaly Detection](https://mlsanity.com/paper/1904.01209/) (2019)
- [ExGAN: Adversarial Generation of Extreme Samples](https://mlsanity.com/paper/2009.08454/) (2020)
- [Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failure](https://mlsanity.com/paper/2007.10088/) (2020)
- [Anomaly Detection using Autoencoders in High Performance Computing Systems](https://mlsanity.com/paper/1811.05269/) (2018)
- [A General Framework For Detecting Anomalous Inputs to DNN Classifiers](https://mlsanity.com/paper/2007.15147/) (2020)
- [GAN Ensemble for Anomaly Detection](https://mlsanity.com/paper/2012.07988/) (2020)
- [Anomaly Detection with Adversarial Dual Autoencoders](https://mlsanity.com/paper/1902.06924/) (2019)
- [The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise](https://mlsanity.com/paper/2007.15220/) (2020)
- [Anomaly Generation using Generative Adversarial Networks in Host Based Intrusion Detection](https://mlsanity.com/paper/1812.04697/) (2018)

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

- [Semisupervised Anomaly Detection using Support Vector Regression with Quantum Kernel](https://mlsanity.com/paper/2308.00583/) (2023)
- [QUACK: Quantum Aligned Centroid Kernel](https://mlsanity.com/paper/2405.00304/) (2024)
- [FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning](https://mlsanity.com/paper/2502.16396/) (2025)

## Abstract (arXiv)

Anomaly detection is a challenging task for machine learning algorithms due to the inherent class imbalance. It is costly and time-demanding to manually analyse the observed data, thus usually only few known anomalies if any are available. Inspired by generative models and the analysis of the hidden activations of neural networks, we introduce a novel unsupervised anomaly detection method called DA3D. Here, we use adversarial autoencoders to generate anomalous counterexamples based on the normal data only. These artificial anomalies used during training allow the detection of real, yet unseen anomalies. With our novel generative approach, we transform the unsupervised task of anomaly detection to a supervised one, which is more tractable by machine learning and especially deep learning methods. DA3D surpasses the performance of state-of-the-art anomaly detection methods in a purely data-driven way, where no domain knowledge is required.