Adversarially Learned Anomaly Detection

Page view(s)
1,523
Checked on Apr 15, 2024
Adversarially Learned Anomaly Detection
Title:
Adversarially Learned Anomaly Detection
Journal Title:
IEEE International Conference on Data Mining 2018
DOI:
Publication URL:
Publication Date:
17 November 2018
Citation:
Abstract:
Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge. As Generative Adversarial Networks (GANs) are able to model the complex high-dimensional distributions of real-world data, they offer a promising approach to address this challenge. In this work, we propose an anomaly detection method, Adversarially Learned Anomaly Detection (ALAD) based on bi-directional GANs, that derives adversarially learned features for the anomaly detection task. ALAD then uses reconstruction errors based on these adversarially learned features to determine if a data sample is anomalous. ALAD builds on recent advances to ensure data-space and latent-space cycle-consistencies and stabilize GAN training, which results in significantly improved anomaly detection performance. ALAD achieves state-of-the-art performance on a range of image and tabular datasets while being several hundred-fold faster at test time than the only published GAN-based method.
License type:
PublisherCopyrights
Funding Info:
Agency for Science, Technology and Research (A*STAR), SERC Strategic Funding (A1718g0045)
Description:
(c) 2018 IEEE.
ISBN:

Files uploaded:

File Size Format Action
alad-v24.pdf 1.34 MB PDF Open