Algorithmic Fairness in Face Morphing Attack Detection

TL;DR

This paper evaluates the fairness of face morphing attack detection algorithms across different ethnic groups, revealing significant biases and emphasizing the need for more equitable MAD solutions.

Contribution

It provides the first comprehensive benchmark of S-MAD algorithms' fairness across ethnicities using a new dataset and introduces quantitative fairness measurement.

Findings

All six S-MAD methods show bias across ethnic groups.

Current MAD algorithms lack fairness and exhibit ethnic bias.

The study highlights the need for bias mitigation in MAD algorithms.

Abstract

Face morphing attacks can compromise Face Recognition System (FRS) by exploiting their vulnerability. Face Morphing Attack Detection (MAD) techniques have been developed in recent past to deter such attacks and mitigate risks from morphing attacks. MAD algorithms, as any other algorithms should treat the images of subjects from different ethnic origins in an equal manner and provide non-discriminatory results. While the promising MAD algorithms are tested for robustness, there is no study comprehensively bench-marking their behaviour against various ethnicities. In this paper, we study and present a comprehensive analysis of algorithmic fairness of the existing Single image-based Morph Attack Detection (S-MAD) algorithms. We attempt to better understand the influence of ethnic bias on MAD algorithms and to this extent, we study the performance of MAD algorithms on a newly created dataset consisting of four different ethnic groups. With Extensive experiments using six different S-MAD techniques, we first present benchmark of detection performance and then measure the quantitative value of the algorithmic fairness for each of them using Fairness Discrepancy Rate (FDR). The results indicate the lack of fairness on all six different S-MAD methods when trained and tested on different ethnic groups suggesting the need for reliable MAD approaches to mitigate the algorithmic bias.