Autoencoders for Anomaly Detection are Unreliable

TL;DR

This paper demonstrates that autoencoders, commonly used for anomaly detection, can fail by perfectly reconstructing anomalies, challenging their reliability and highlighting potential safety risks.

Contribution

It provides a theoretical and empirical analysis showing autoencoders can reconstruct anomalies accurately, undermining their effectiveness for anomaly detection.

Findings

Linear autoencoders can perfectly reconstruct out-of-distribution data

Autoencoders may extrapolate undesirably, leading to false negatives

Reconstruction failure assumptions do not always hold in practice

Abstract

Autoencoders are frequently used for anomaly detection, both in the unsupervised and semi-supervised settings. They rely on the assumption that when trained using the reconstruction loss, they will be able to reconstruct normal data more accurately than anomalous data. Some recent works have posited that this assumption may not always hold, but little has been done to study the validity of the assumption in theory. In this work we show that this assumption indeed does not hold, and illustrate that anomalies, lying far away from normal data, can be perfectly reconstructed in practice. We revisit the theory of failure of linear autoencoders for anomaly detection by showing how they can perfectly reconstruct out of bounds, or extrapolate undesirably, and note how this can be dangerous in safety critical applications. We connect this to non-linear autoencoders through experiments on both tabular data and real-world image data, the two primary application areas of autoencoders for anomaly detection.