Fairness Properties of Face Recognition and Obfuscation Systems

2021/08/05 by Harrison Rosenberg, Rosenberg, Harrison, Brian Tang +5 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Privacy-Preserving Technologies in Data #cs.AI #cs.CV

paper · pdf · doi:10.48550/arxiv.2108.02707

openalex publication_date 2021/08/05 · arxiv created 2022/09/16 · arxiv updated 2022/09/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The proliferation of automated face recognition in the commercial and government sectors has caused significant privacy concerns for individuals. One approach to address these privacy concerns is to employ evasion attacks against the metric embedding networks powering face recognition systems: Face obfuscation systems generate imperceptibly perturbed images that cause face recognition systems to misidentify the user. Perturbed faces are generated on metric embedding networks, which are known to be unfair in the context of face recognition. A question of demographic fairness naturally follows: are there demographic disparities in face obfuscation system performance? We answer this question with an analytical and empirical exploration of recent face obfuscation systems. Metric embedding networks are found to be demographically aware: face embeddings are clustered by demographic. We show how this clustering behavior leads to reduced face obfuscation utility for faces in minority groups. An intuitive analytical model yields insight into these phenomena.

Citations

• Learning Face Representation from Scratch
• THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVED
• YFCC100M
• Equality of Opportunity in Supervised Learning
• Lipschitz regularity of deep neural networks: analysis and efficient estimation
• Overlearning Reveals Sensitive Attributes
• Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
• FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age

Cited by

• Sy-FAR: Symmetry-based Fair Adversarial Robustness

Related

• FairDeFace: Evaluating the Fairness and Adversarial Robustness of Face Obfuscation Methods
• The More Secure, The Less Equally Usable: Gender and Ethnicity (Un)fairness of Deep Face Recognition along Security Thresholds
• Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in Facial Recognition
• A Study of Face Obfuscation in ImageNet
• Are Commercial Face Detection Models as Biased as Academic Models?