Towards Fair Deep Anomaly Detection

TL;DR

This paper introduces Deep Fair SVDD, a novel deep anomaly detection architecture that incorporates fairness by de-correlating sensitive attributes from learned representations, achieving fairer results with minimal performance loss.

Contribution

The paper proposes a new adversarial training approach for fair deep anomaly detection, addressing social bias while maintaining detection accuracy.

Findings

Existing deep anomaly detection methods are unfair.

Deep Fair SVDD effectively reduces unfairness.

Minimal loss in anomaly detection performance.

Abstract

Anomaly detection aims to find instances that are considered unusual and is a fundamental problem of data science. Recently, deep anomaly detection methods were shown to achieve superior results particularly in complex data such as images. Our work focuses on deep one-class classification for anomaly detection which learns a mapping only from the normal samples. However, the non-linear transformation performed by deep learning can potentially find patterns associated with social bias. The challenge with adding fairness to deep anomaly detection is to ensure both making fair and correct anomaly predictions simultaneously. In this paper, we propose a new architecture for the fair anomaly detection approach (Deep Fair SVDD) and train it using an adversarial network to de-correlate the relationships between the sensitive attributes and the learned representations. This differs from how fairness is typically added namely as a regularizer or a constraint. Further, we propose two effective fairness measures and empirically demonstrate that existing deep anomaly detection methods are unfair. We show that our proposed approach can remove the unfairness largely with minimal loss on the anomaly detection performance. Lastly, we conduct an in-depth analysis to show the strength and limitations of our proposed model, including parameter analysis, feature visualization, and run-time analysis.