# On Biased Behavior of GANs for Face Verification

arXiv: https://arxiv.org/abs/2208.13061 · HTML: https://mlsanity.com/paper/2208.13061/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 27 Aug 2022.

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

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning](https://mlsanity.com/paper/2004.11660/) (2020)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [Face Recognition: Too Bias, or Not Too Bias?](https://mlsanity.com/paper/2002.06483/) (2020)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [Fair Contrastive Learning for Facial Attribute Classification](https://mlsanity.com/paper/2203.16209/) (2022)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [Surpassing Human-Level Face Verification Performance on LFW with GaussianFace](https://mlsanity.com/paper/1404.3840/) (2014)
- [Characterizing Bias in Classifiers using Generative Models](https://mlsanity.com/paper/1906.11891/) (2019)
- [Learning Facial Representations from the Cycle-consistency of Face](https://mlsanity.com/paper/2108.03427/) (2021)
- [FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations](https://mlsanity.com/paper/2202.06240/) (2022)
- [Evaluation-oriented Knowledge Distillation for Deep Face Recognition](https://mlsanity.com/paper/2206.02325/) (2022)
- [Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation](https://mlsanity.com/paper/2203.14327/) (2022)
- [Learn to Cluster Faces via Pairwise Classification](https://mlsanity.com/paper/2205.13117/) (2022)

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

- [Bias mitigation techniques in image classification: fair machine learning in human heritage collections](https://mlsanity.com/paper/2303.11449/) (2023)

## Abstract (arXiv)

Deep Learning systems need large data for training. Datasets for training face verification systems are difficult to obtain and prone to privacy issues. Synthetic data generated by generative models such as GANs can be a good alternative. However, we show that data generated from GANs are prone to bias and fairness issues. Specifically, GANs trained on FFHQ dataset show biased behavior towards generating white faces in the age group of 20-29. We also demonstrate that synthetic faces cause disparate impact, specifically for race attribute, when used for fine tuning face verification systems.