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

  title={Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators},
  author={Jan-Philipp Schulze and Philip Sperl and Konstantin B{\"o}ttinger},
  journal={2022 International Joint Conference on Neural Networks (IJCNN)},
Anomaly detection is a challenging task for machine learning methods 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… 

Figures and Tables from this paper



Deep Anomaly Detection with Deviation Networks

A novel anomaly detection framework and its instantiation that can be trained substantially more data-efficiently and achieves significantly better anomaly scoring than state-of-the-art competing methods is introduced.

Fence GAN: Towards Better Anomaly Detection

With the modified GAN loss proposed, the anomaly detection method, called Fence GAN (FGAN), directly uses the discriminator score as an anomaly threshold and the experimental results show that FGAN yields the best anomaly classification accuracy compared to state-of-the-art methods.


This paper focuses on the classification of segmented local bright spots as either calcification or noncalcification in mammographic images and seven classifiers (linear and quadratic classifiers, binary decision trees, standard backpropagation network, 2 dynamic neural networks, and a K-nearest neighbor) are compared.

Adversarial Autoencoders

This paper shows how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization, and performed experiments on MNIST, Street View House Numbers and Toronto Face datasets.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a

Activation Anomaly Analysis

It is shown that the hidden activation values contain information useful to distinguish between normal and anomalous samples, and the semi-supervised anomaly detection method allows to inspect large amounts of data for anomalies across various applications.

Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection

A Deep Autoencoding Gaussian Mixture Model (DAGMM) for unsupervised anomaly detection, which significantly outperforms state-of-the-art anomaly detection techniques, and achieves up to 14% improvement based on the standard F1 score.

Wasserstein Generative Adversarial Networks

This work introduces a new algorithm named WGAN, an alternative to traditional GAN training that can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches.

Wasserstein GAN

The problem this paper is concerned with is that of unsupervised learning, what does it mean to learn a probability distribution and how to define a parametric family of densities.

UCI Machine Learning Repository

  • University of California, Irvine, School of Information and Computer Sciences,
  • 2017