Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
Not on the map. Why?
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 51 references that are in the map. First posted on arXiv 12 Jan 2021.
Builds on
29 of 51 references.
References · 29
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
- 2018Deep Anomaly Detection with Outlier Exposurecited by 939
- 2017Wasserstein GANcited by 635
- 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
- 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
- 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
- 2015Adversarial Autoencoderscited by 359
- 2019Deep Semi-Supervised Anomaly Detectioncited by 290
- 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
- 2020Classification-Based Anomaly Detection for General Datacited by 210
17 more
- 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
- 2019Deep Anomaly Detection with Deviation Networkscited by 152
- 2019Seeing What a GAN Cannot Generatecited by 148
- 2018Adversarially Learned Anomaly Detectioncited by 115
- 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
- 2019Robust Anomaly Detection in Images using Adversarial Autoencoderscited by 38
- 2018DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GANcited by 34
- 2018One-Class Adversarial Nets for Fraud Detectioncited by 33
- 2019Fence GAN: Towards Better Anomaly Detectioncited by 32
- 2020ExGAN: Adversarial Generation of Extreme Samplescited by 28
- 2020Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failurecited by 27
- 2018Anomaly Detection using Autoencoders in High Performance Computing Systemscited by 25
- 2020A General Framework For Detecting Anomalous Inputs to DNN Classifierscited by 24
- 2020GAN Ensemble for Anomaly Detectioncited by 22
- 2019Anomaly Detection with Adversarial Dual Autoencoderscited by 16
- 2020The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noisecited by 15
- 2018Anomaly Generation using Generative Adversarial Networks in Host Based Intrusion Detectioncited by 7
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.