Anomaly Detection using One-Class Neural Networks

TL;DR

This paper introduces OC-NN, a novel deep learning model that learns data representations tailored for anomaly detection, outperforming traditional hybrid methods on complex datasets.

Contribution

The paper presents OC-NN, a one-class neural network that integrates representation learning with anomaly detection, unlike previous methods that separate these steps.

Findings

OC-NN performs on par with state-of-the-art methods on complex datasets.

OC-NN outperforms traditional shallow methods in certain scenarios.

Data representation in OC-NN is driven by the anomaly detection objective.

Abstract

We propose a one-class neural network (OC-NN) model to detect anomalies in complex data sets. OC-NN combines the ability of deep networks to extract a progressively rich representation of data with the one-class objective of creating a tight envelope around normal data. The OC-NN approach breaks new ground for the following crucial reason: data representation in the hidden layer is driven by the OC-NN objective and is thus customized for anomaly detection. This is a departure from other approaches which use a hybrid approach of learning deep features using an autoencoder and then feeding the features into a separate anomaly detection method like one-class SVM (OC-SVM). The hybrid OC-SVM approach is sub-optimal because it is unable to influence representational learning in the hidden layers. A comprehensive set of experiments demonstrate that on complex data sets (like CIFAR and GTSRB), OC-NN performs on par with state-of-the-art methods and outperformed conventional shallow methods in some scenarios.