Lune

USENIX Security2023Top-tier venue

Fairness Properties of Face Recognition and Obfuscation Systems

Harrison Rosenberg, Brian Tang, Kassem Fawaz, Somesh Jha

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • SoK: Anti-Facial Recognition Technology cites Towards Evaluating the Robustness of Neural Networks
  • SoK: Anti-Facial Recognition Technology cites Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
  • SoK: Anti-Facial Recognition Technology cites Data Poisoning Won't Save You From Facial Recognition
  • Data Poisoning Won't Save You From Facial Recognition cites Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
  • To be Robust or to be Fair: Towards Fairness in Adversarial Training cites Towards Evaluating the Robustness of Neural Networks
  • To be Robust or to be Fair: Towards Fairness in Adversarial Training cites Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
  • Sy-FAR: Symmetry-based Fair Adversarial Robustness cites Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
  • Sy-FAR: Symmetry-based Fair Adversarial Robustness cites To be Robust or to be Fair: Towards Fairness in Adversarial Training
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric LearningNatalie Dullerud, Karsten Roth, Kimia Hamidieh, Nicolas Papernot et al.ICLR 2022 · 16 citations
  2. Synthesizing Precise Static Analyzers for Automatic DifferentiationJacob Laurel, Siyuan Brant Qian, Gagandeep Singh, Sasa MisailovicOOPSLA 2023 · 8 citations
  3. SoK: Anti-Facial Recognition TechnologyEmily Wenger, Shawn Shan, Haitao Zheng, Ben Y. ZhaoS&P 2023
  4. Sy-FAR: Symmetry-based Fair Adversarial RobustnessHaneen Najjar, Eyal Ronen, Mahmood SharifUSENIX Security 2026

Builds on7

  1. Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, David A. WagnerS&P 2017 · 9,786 citations
  2. Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face RecognitionMahmood Sharif, Sruti Bhagavatula, Lujo Bauer, Michael K. ReiterCCS 2016 · 1,765 citations
  3. To be Robust or to be Fair: Towards Fairness in Adversarial TrainingHan Xu, Xiaorui Liu, Yaxin Li, Anil K. Jain et al.ICML 2021 · 218 citations
  4. Overlearning Reveals Sensitive AttributesCongzheng Song, Vitaly ShmatikovICLR 2020 · 177 citations
  5. Data Poisoning Won't Save You From Facial RecognitionEvani Radiya-Dixit, Sanghyun Hong, Nicholas Carlini, Florian TramèrICLR 2022 · 67 citations

Related papers

  1. Towards Poisoning Fair RepresentationsTianci Liu, Haoyu Wang, Feijie Wu, Hengtong Zhang et al.ICLR 2024 · 3 citations
  2. Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep ModelsZhibo Wang, Xiaowei Dong, Henry Xue, Zhifei Zhang et al.CVPR 2022 · 49 citations
  3. Invariant Feature Regularization for Fair Face RecognitionJiali Ma, Zhongqi Yue, Tomoyuki Kagaya, Tomoki Suzuki et al.ICCV 2023 · 15 citations
  4. Mitigating Face Recognition Bias via Group Adaptive ClassifierSixue Gong, Xiaoming Liu, Anil K. JainCVPR 2021
  5. FaceObfuscator: Defending Deep Learning-based Privacy Attacks with Gradient Descent-resistant Features in Face RecognitionShuaifan Jin, He Wang, Zhibo Wang, Feng Xiao et al.USENIX Security 2024 · 9 citations
Dusk over the sea between two cliffs drawn in fine vertical lines