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

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.

Anomaly Detection by Recombining Gated Unsupervised Experts

Inspired by mixture-of-experts models and the analysis of the hidden activations of neural networks, we introduce a novel unsupervised anomaly detection method called ARGUE. Multiple expert networks, which specialise on parts of the data deemed as normal, contribute to the overall anomaly score. For its final decision, ARGUE weights the distributed knowledge across the expert systems using a gated mixture-of-experts architecture. ARGUE achieves superior detection performance across several domains in a purely data-driven fashion and is more robust to noisy data sets than other state-of-the-art anomaly detection methods.