Evaluating Trustworthiness and Racial Bias in Face Recognition APIs Using Deepfakes

Evaluating Trustworthiness and Racial Bias in Face Recognition APIs Using Deepfakes

We evaluate the racial bias in face recognition application programming interfaces (APIs) using real and deepfake celebrity images. We use deepfake generation methods to introduce small, imperceptible changes to the real images to shift the racial class of predictions, showing how deepfake images ex...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer (Long Beach, Calif.) Calif.), 2023-05, Vol.56 (5), p.51-61
Hauptverfasser: Tariq, Shahroz, Jeon, Sowon, Woo, Simon S.
Format: Artikel
Sprache:eng
Schlagworte:
Application programming interface
Application programming interfaces
Bias
Cultural aspects
Deception
Deepfakes
Face recognition
Image recognition
Trust computing
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We evaluate the racial bias in face recognition application programming interfaces (APIs) using real and deepfake celebrity images. We use deepfake generation methods to introduce small, imperceptible changes to the real images to shift the racial class of predictions, showing how deepfake images exacerbated racial bias in web-based face recognition APIs.
ISSN:0018-9162
1558-0814
DOI:10.1109/MC.2023.3234978