Efficient GAN-Based Anomaly Detection

TL;DR

This paper introduces an efficient GAN-based approach for anomaly detection that achieves state-of-the-art results on image and network intrusion datasets, significantly improving speed over previous methods.

Contribution

It leverages recent GAN models to enhance anomaly detection performance and drastically reduces test time compared to prior GAN-based approaches.

Findings

Achieved state-of-the-art performance on image datasets.

Demonstrated superior speed at test time.

Effective on network intrusion detection datasets.

Abstract

Generative adversarial networks (GANs) are able to model the complex highdimensional distributions of real-world data, which suggests they could be effective for anomaly detection. However, few works have explored the use of GANs for the anomaly detection task. We leverage recently developed GAN models for anomaly detection, and achieve state-of-the-art performance on image and network intrusion datasets, while being several hundred-fold faster at test time than the only published GAN-based method.