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

arXiv: https://arxiv.org/abs/2302.07917 · HTML: https://mlsanity.com/paper/2302.07917/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 15 Feb 2023.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)
- [Learning Controllable Fair Representations](https://mlsanity.com/paper/1812.04218/) (2018)
- [Practical Blind Membership Inference Attack via Differential Comparisons](https://mlsanity.com/paper/2101.01341/) (2021)
- [Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction](https://mlsanity.com/paper/1807.00199/) (2018)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces](https://mlsanity.com/paper/1907.05345/) (2019)
- [PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition](https://mlsanity.com/paper/2108.03764/) (2021)
- [Balancing Biases and Preserving Privacy on Balanced Faces in the Wild](https://mlsanity.com/paper/2103.09118/) (2021)
- [TARA: Training and Representation Alteration for AI Fairness and Domain Generalization](https://mlsanity.com/paper/2012.06387/) (2020)
- [Defending Medical Image Diagnostics against Privacy Attacks using Generative Methods](https://mlsanity.com/paper/2103.03078/) (2021)
- [Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics](https://mlsanity.com/paper/2004.13515/) (2020)

## Built on by (most cited first, 1 of 1)

- [Holistic Survey of Privacy and Fairness in Machine Learning](https://mlsanity.com/paper/2307.15838/) (2023)

## 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.