paper-with-me

Papers

Fairness Properties of Face Recognition and Obfuscation Systems

2021-08-05 · Harrison Rosenberg, Brian Tang, Kassem Fawaz, Somesh Jha

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.

📄 PDF Abstract BibTeX arXiv:2108.02707

Code (1)

wi-pi/fairness_face_obfuscation 공식 구현 tf

Tasks

Face RecognitionFairness

Similar Papers 제목 키워드 기반

FairDeFace: Evaluating the Fairness and Adversarial Robustness of Face Obfuscation Methods

2025-03-11 · Seyyed Mohammad Sadegh Moosavi Khorzooghi, Poojitha Thota, Mohit Singhal, Abolfazl Asudeh 외

The lack of a common platform and benchmark datasets for evaluating face obfuscation methods has been a challenge, with every method being tested using arbitrary experiments, datasets, and metrics. While prior work has d…

Adversarial RobustnessFace DetectionFace RecognitionFairness

Evaluating Proposed Fairness Models for Face Recognition Algorithms

2022-03-09 · John J. Howard, Eli J. Laird, Yevgeniy B. Sirotin, Rebecca E. Rubin 외

The development of face recognition algorithms by academic and commercial organizations is growing rapidly due to the onset of deep learning and the widespread availability of training data. Though tests of face recognit…

Face RecognitionFairness

A Study of Face Obfuscation in ImageNet

2021-03-10 · Kaiyu Yang, Jacqueline Yau, Li Fei-Fei, Jia Deng 외

Face obfuscation (blurring, mosaicing, etc.) has been shown to be effective for privacy protection; nevertheless, object recognition research typically assumes access to complete, unobfuscated images. In this paper, we e…

AttributeObjectobject-detectionObject Detection+3

AdvFaces: Adversarial Face Synthesis

2019-08-14 · Debayan Deb, Jianbang Zhang, Anil K. Jain

Face recognition systems have been shown to be vulnerable to adversarial examples resulting from adding small perturbations to probe images. Such adversarial images can lead state-of-the-art face recognition systems to f…

Face GenerationFace Recognition

Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacy

2024-02-16 · Songjie Xie, Youlong Wu, Jiaxuan Li, Ming Ding 외

As machine learning (ML) becomes more prevalent in human-centric applications, there is a growing emphasis on algorithmic fairness and privacy protection. While previous research has explored these areas as separate obje…

FairnessRepresentation Learning