Loading…

Adversarial Regularized Reconstruction for Anomaly Detection and Generation

We propose ARN, a semisupervised anomaly detection and generation method based on adversarial reconstruction. ARN exploits a regularized autoencoder to optimize the reconstruction of variants of normal examples with minimal differences, that are recognized as outliers. The combination of regularizat...

Full description

Saved in:
Bibliographic Details
Main Authors: Liguori, Angelica, Manco, Giuseppe, Pisani, Francesco Sergio, Ritacco, Ettore
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose ARN, a semisupervised anomaly detection and generation method based on adversarial reconstruction. ARN exploits a regularized autoencoder to optimize the reconstruction of variants of normal examples with minimal differences, that are recognized as outliers. The combination of regularization and adversarial reconstruction helps to stabilize the learning process, which results in both realistic outlier generation and substantial detection capability. Experiments on several benchmark datasets show that our model improves the current state-of-the-art by valuable margins because of its ability to model the true boundaries of the data manifold.
ISSN:2374-8486
DOI:10.1109/ICDM51629.2021.00145