mlsanityData to 7 Oct 2026

Evaluating Trade-offs in Computer Vision Between Attribute Privacy, Fairness and Utility

arXiv 2302.07917 ↗First posted 15 Feb 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper investigates to what degree and magnitude tradeoffs exist between utility, fairness and attribute privacy in computer vision. Regarding privacy, we look at this important problem specifically in the context of attribute inference attacks, a less addressed form of privacy. To create a variety of models with different preferences, we use adversarial methods to intervene on attributes relating to fairness and privacy. We see that that certain tradeoffs exist between fairness and utility, privacy and utility, and between privacy and fairness. The results also show that those tradeoffs and interactions are more complex and nonlinear between the three goals than intuition would suggest.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 15 Feb 2023.

Builds on

25 of 36 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  10. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  11. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  12. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
13 more
  1. 2020Fairness in Machine Learning: A Surveycited by 369
  2. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  3. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  4. 2018Learning Controllable Fair Representationscited by 83
  5. 2018Achieving Fairness through Adversarial Learning: an Application to Recidivism Predictioncited by 77
  6. 2018Differentially Private Fair Learningcited by 76
  7. 2021Practical Blind Membership Inference Attack via Differential Comparisonscited by 73
  8. 2019Evaluation of Retinal Image Quality Assessment Networks in Different Color-spacescited by 57
  9. 2021PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognitioncited by 38
  10. 2021Balancing Biases and Preserving Privacy on Balanced Faces in the Wildcited by 17
  11. 2020TARA: Training and Representation Alteration for AI Fairness and Domain Generalizationcited by 10
  12. 2021Defending Medical Image Diagnostics against Privacy Attacks using Generative Methodscited by 8
  13. 2020Addressing Artificial Intelligence Bias in Retinal Disease Diagnosticscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Holistic Survey of Privacy and Fairness in Machine Learningcited by 4