English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The study of bias in Machine Learning is receiving a lot of attention inrecent years, however, few only papers deal explicitly with the problem of racebias in face anti-spoofing. In this paper, we present a systematic study ofrace bias in face anti-spoofing with three key characteristics: the focus is onanalysing potential bias in the bona fide errors, where significant ethical andlegal issues lie; the analysis is not restricted to the final binary outcomesof the classifier, but also covers the classifier's scalar responses and itslatent space; the threshold determining the operating point of the classifieris considered a variable. We demonstrate the proposed bias analysis process ona VQ-VAE based face anti-spoofing algorithm, trained on the Replay Attack andthe Spoof in the Wild (SiW) databases, and analysed for bias on the SiW andRacial Faces in the Wild (RFW), databases. The results demonstrate that racebias is not necessarily the result of different mean response values among thevarious populations. Instead, it can be better understood as the combinedeffect of several possible characteristics of the response distributions:different means; different variances; bimodal behaviour; existence of outliers.

Race Bias Analysis of Bona Fide Errors in face anti-spoofing