Fairness Index Measures to Evaluate Bias in Biometric Recognition
This work addresses demographic fairness in biometric systems, which is crucial for societal impact and applicability in private and public domains, but it is incremental as it builds on existing fairness measures by focusing on pre-decision data.
The authors tackled the problem of demographic bias in biometric verification systems by introducing multiple fairness measures based on pre-decision score distributions, proposing variants for combining group contributions and a weighing strategy to mitigate dataset imbalance, with results illustrated numerically and graphically on synthetic data.
The demographic disparity of biometric systems has led to serious concerns regarding their societal impact as well as applicability of such systems in private and public domains. A quantitative evaluation of demographic fairness is an important step towards understanding, assessment, and mitigation of demographic bias in biometric applications. While few, existing fairness measures are based on post-decision data (such as verification accuracy) of biometric systems, we discuss how pre-decision data (score distributions) provide useful insights towards demographic fairness. In this paper, we introduce multiple measures, based on the statistical characteristics of score distributions, for the evaluation of demographic fairness of a generic biometric verification system. We also propose different variants for each fairness measure depending on how the contribution from constituent demographic groups needs to be combined towards the final measure. In each case, the behavior of the measure has been illustrated numerically and graphically on synthetic data. The demographic imbalance in benchmarking datasets is often overlooked during fairness assessment. We provide a novel weighing strategy to reduce the effect of such imbalance through a non-linear function of sample sizes of demographic groups. The proposed measures are independent of the biometric modality, and thus, applicable across commonly used biometric modalities (e.g., face, fingerprint, etc.).