Probabilistic Outlier Detection and Generation

TL;DR

This paper introduces WALDO, a novel neural network-based method that detects and generates outliers by modeling data as probability distributions, demonstrating effectiveness on various datasets and applications.

Contribution

The paper presents WALDO, a unique approach combining outlier detection and generation using Wasserstein autoencoders, addressing a gap in existing methods.

Findings

Effective outlier detection on MNIST, CIFAR10, KDD99

Successful outlier generation for intrusion simulation

Robustness demonstrated across diverse datasets

Abstract

A new method for outlier detection and generation is introduced by lifting data into the space of probability distributions which are not analytically expressible, but from which samples can be drawn using a neural generator. Given a mixture of unknown latent inlier and outlier distributions, a Wasserstein double autoencoder is used to both detect and generate inliers and outliers. The proposed method, named WALDO (Wasserstein Autoencoder for Learning the Distribution of Outliers), is evaluated on classical data sets including MNIST, CIFAR10 and KDD99 for detection accuracy and robustness. We give an example of outlier detection on a real retail sales data set and an example of outlier generation for simulating intrusion attacks. However we foresee many application scenarios where WALDO can be used. To the best of our knowledge this is the first work that studies both outlier detection and generation together.