• Corpus ID: 236924628

Fairness Properties of Face Recognition and Obfuscation Systems

  title={Fairness Properties of Face Recognition and Obfuscation Systems},
  author={Harrison Rosenberg and Brian Tang and Kassem Fawaz and Somesh Jha},
  • Harrison Rosenberg, Brian Tang, +1 author Somesh Jha
  • Published 5 August 2021
  • Computer Science
  • ArXiv
The proliferation of automated facial recognition in various commercial and government sectors has caused significant privacy concerns for individuals. A recent and popular approach to address these privacy concerns is to employ evasion attacks against the metric embedding networks powering facial recognition systems. Face obfuscation systems generate imperceptible perturbations, when added to an image, cause the facial recognition system to misidentify the user. The key to these approaches is… 
SoK: Anti-Facial Recognition Technology
This paper creates a systematic framework for analyzing the benefits and tradeoffs of different AFR approaches and considers both technical and social challenges facing AFR tools and proposes directions for future research in this field.


LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition
This work develops their own adversarial filter that accounts for the entire image processing pipeline and is demonstrably effective against industrial-grade pipelines that include face detection and large scale databases.
Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
The database contains labeled face photographs spanning the range of conditions typically encountered in everyday life, and exhibits “natural” variability in factors such as pose, lighting, race, accessories, occlusions, and background.
Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
Fawkes is a system that helps individuals inoculate their images against unauthorized facial recognition models by helping users add imperceptible pixel-level changes to their own photos before releasing them, and is robust against a variety of countermeasures that try to detect or disrupt image cloaks.
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification
It is shown that the highest error involves images of dark-skinned women, while the most accurate result is for light-skinned men, in commercial API-based classifiers of gender from facial images, including IBM Watson Visual Recognition.
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
Concept Activation Vectors (CAVs) are introduced, which provide an interpretation of a neural net's internal state in terms of human-friendly concepts, and may be used to explore hypotheses and generate insights for a standard image classification network as well as a medical application.
The concept of face, as it is developed by Goffman, has strong conceptual links with the notion of a ‘looking-glass’ self outlined by Adam Smith and developed sociologically by Cooley. It also has
Visualizing Data using t-SNE
We present a new technique called “t-SNE” that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map. The technique is a variation of Stochastic
Towards Deep Learning Models Resistant to Adversarial Attacks
This work studies the adversarial robustness of neural networks through the lens of robust optimization, and suggests the notion of security against a first-order adversary as a natural and broad security guarantee.
VGGFace2: A Dataset for Recognising Faces across Pose and Age
A new large-scale face dataset named VGGFace2 is introduced, which contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject, and the automated and manual filtering stages to ensure a high accuracy for the images of each identity are described.
FaceNet: A unified embedding for face recognition and clustering
A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.