NFAD: Fixing anomaly detection using normalizing flows

TL;DR

This paper introduces a novel training method for anomaly detection that incorporates known anomalies by using normalizing flows to generate pseudo-anomalous samples, improving detection performance especially when some anomalies are known.

Contribution

The work reformulates one-class classification as a binary problem using pseudo-anomalous samples generated from normalizing flows, allowing integration of known anomalies into training.

Findings

Comparable performance on one-class problems

Superior results with known anomalies

Effective incorporation of anomaly samples

Abstract

Anomaly detection is a challenging task that frequently arises in practically all areas of industry and science, from fraud detection and data quality monitoring to finding rare cases of diseases and searching for new physics. Most of the conventional approaches to anomaly detection, such as one-class SVM and Robust Auto-Encoder, are one-class classification methods, i.e. focus on separating normal data from the rest of the space. Such methods are based on the assumption of separability of normal and anomalous classes, and subsequently do not take into account any available samples of anomalies. Nonetheless, in practical settings, some anomalous samples are often available; however, usually in amounts far lower than required for a balanced classification task, and the separability assumption might not always hold. This leads to an important task -- incorporating known anomalous samples into training procedures of anomaly detection models. In this work, we propose a novel model-agnostic training procedure to address this task. We reformulate one-class classification as a binary classification problem with normal data being distinguished from pseudo-anomalous samples. The pseudo-anomalous samples are drawn from low-density regions of a normalizing flow model by feeding tails of the latent distribution into the model. Such an approach allows to easily include known anomalies into the training process of an arbitrary classifier. We demonstrate that our approach shows comparable performance on one-class problems, and, most importantly, achieves comparable or superior results on tasks with variable amounts of known anomalies.