mlsanityData to 7 Oct 2026

Fairness Properties of Face Recognition and Obfuscation Systems

arXiv 2108.02707 ↗First posted 5 Aug 2021cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 39 of its 86 references that are in the map. First posted on arXiv 5 Aug 2021.

Builds on

39 of 86 references.

References · 39

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  11. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  12. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
27 more
  1. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  2. 2018Robustness May Be at Odds with Accuracycited by 873
  3. 2017Spectrally-normalized margin bounds for neural networkscited by 681
  4. 2017Exploring Generalization in Deep Learningcited by 595
  5. 2019Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networkscited by 562
  6. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  7. 2014Learning Face Representation from Scratchcited by 451
  8. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  9. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 413
  10. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  11. 2018Adversarially Robust Generalization Requires More Datacited by 318
  12. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  13. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181
  14. 2017The Space of Transferable Adversarial Examplescited by 156
  15. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  16. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
  17. 2019FairFace: Face Attribute Dataset for Balanced Race, Gender, and Agecited by 87
  18. 2019Diversity in Facescited by 77
  19. 2019Overlearning Reveals Sensitive Attributescited by 74
  20. 2020Fairness Through Robustness: Investigating Robustness Disparity in Deep Learningcited by 55
  21. 2020SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learningcited by 50
  22. 2021Data Poisoning Won't Save You From Facial Recognitioncited by 45
  23. 2019Disparate Vulnerability to Membership Inference Attackscited by 33
  24. 2018RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applicationscited by 27
  25. 2020Sharp Statistical Guarantees for Adversarially Robust Gaussian Classificationcited by 27
  26. 2020Face-Off: Adversarial Face Obfuscationcited by 25
  27. 2020FoggySight: A Scheme for Facial Lookup Privacycited by 12

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 1; 2024: 1; 2025: 3.

9 papers.

  1. 2021SoK: Anti-Facial Recognition Technologycited by 16
  2. 2022Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learningcited by 11
  3. 2022Explaining Bias in Deep Face Recognition via Image Characteristicscited by 6
  4. 2023Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groupscited by 6
  5. 2022StyleGAN as a Utility-Preserving Face De-identification Methodcited by 2
  6. 2025Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunitiescited by 2
  7. 2024Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacycited by 1
  8. 2025FairDeFace: Evaluating the Fairness and Adversarial Robustness of Face Obfuscation Methodscited by 0
  9. 2025Sy-FAR: Symmetry-based Fair Adversarial Robustnesscited by 0