Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors

TL;DR

Red PANDA introduces a novel anomaly detection method that enables exclusion of nuisance attributes, learning representations free of irrelevant information, thereby improving detection accuracy without needing to specify relevant attributes.

Contribution

It presents a new anomaly detection technique that removes nuisance factors from representations, allowing operators to ignore irrelevant attributes without prior knowledge of relevant ones.

Findings

Effective at removing nuisance attributes from representations

Improves anomaly detection accuracy in empirical tests

Does not require specifying relevant attributes beforehand

Abstract

Anomaly detection methods strive to discover patterns that differ from the norm in a semantic way. This goal is ambiguous as a data point differing from the norm by an attribute e.g., age, race or gender, may be considered anomalous by some operators while others may consider this attribute irrelevant. Breaking from previous research, we present a new anomaly detection method that allows operators to exclude an attribute from being considered as relevant for anomaly detection. Our approach then learns representations which do not contain information over the nuisance attributes. Anomaly scoring is performed using a density-based approach. Importantly, our approach does not require specifying the attributes that are relevant for detecting anomalies, which is typically impossible in anomaly detection, but only attributes to ignore. An empirical investigation is presented verifying the effectiveness of our approach.