# Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model

arXiv: https://arxiv.org/abs/2402.09786 · HTML: https://mlsanity.com/paper/2402.09786/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 48 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Builds on (most cited first, 16 of 16)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [StoryGAN: A Sequential Conditional GAN for Story Visualization](https://mlsanity.com/paper/1812.02784/) (2018)
- [Diversity in Faces](https://mlsanity.com/paper/1901.10436/) (2019)
- [Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis](https://mlsanity.com/paper/1701.05927/) (2017)
- [Synthetic Examples Improve Generalization for Rare Classes](https://mlsanity.com/paper/1904.05916/) (2019)
- [Studying Bias in GANs through the Lens of Race](https://mlsanity.com/paper/2209.02836/) (2022)
- [Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English](https://mlsanity.com/paper/2209.02145/) (2022)

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

- [Accuracy and Fairness of Facial Recognition Technology in Low-Quality Police Images: An Experiment With Synthetic Faces](https://mlsanity.com/paper/2505.14320/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GANs) generate photorealistic faces that are often indistinguishable by humans from real faces. While biases in machine learning models are often assumed to be due to biases in training data, we find pathological internal color and luminance biases in the discriminator of a pre-trained StyleGAN3-r model that are not explicable by the training data. We also find that the discriminator systematically stratifies scores by both image- and face-level qualities and that this disproportionately affects images across gender, race, and other categories. We examine axes common in research on stereotyping in social psychology.