A Lipschitz-constrained anomaly discriminator framework

05/26/2019
by   Alexander Tong, et al.
0

Anomaly detection is a problem of great interest in medicine, finance, and other fields where error and fraud need to be detected and corrected. Most deep anomaly detection methods rely on autoencoder reconstruction error. However, we show that this approach has limited value. First, this approach starts to perform poorly when either noise or anomalies contaminate training data, even to a small extent. Second, this approach cannot detect anomalous but simple to reconstruct points. This can be seen even in relatively simple examples, such as feeding a black image to detectors trained on MNIST digits. Here, we introduce a new discriminator-based unsupervised Lipschitz anomaly detector (LAD). We train a Wasserstein discriminator, similar to the ones used in GANs, to detect the difference between the training data and corruptions of the training data. We show that this procedure successfully detects unseen anomalies with guarantees on those that have a certain Wasserstein distance from the data or corrupted training set. Finally, we show results of this system in an electronic medical record dataset of HIV-positive veterans from the veterans aging cohort study (VACS) to establish usability in a medical setting.

READ FULL TEXT

page 6

page 15

research
05/17/2023

Reconstruction Error-based Anomaly Detection with Few Outlying Examples

Reconstruction error-based neural architectures constitute a classical d...
research
10/11/2018

MDGAN: Boosting Anomaly Detection Using Multi-Discriminator Generative Adversarial Networks

Anomaly detection is often considered a challenging field of machine lea...
research
03/19/2023

PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies

Due to the rarity of anomalous events, video anomaly detection is typica...
research
10/19/2021

Learning Not to Reconstruct Anomalies

Video anomaly detection is often seen as one-class classification (OCC) ...
research
09/05/2023

Resilient VAE: Unsupervised Anomaly Detection at the SLAC Linac Coherent Light Source

Significant advances in utilizing deep learning for anomaly detection ha...
research
03/25/2022

Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies

Recently, anomaly scores have been formulated using reconstruction loss ...
research
04/16/2020

Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm

A popular method for anomaly detection is to use the generator of an adv...

Please sign up or login with your details

Forgot password? Click here to reset