# Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing

arXiv: https://arxiv.org/abs/2007.13632 · HTML: https://mlsanity.com/paper/2007.13632/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 30 of 32)

- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [Unsupervised Learning of Debiased Representations with Pseudo-Attributes](https://mlsanity.com/paper/2108.02943/) (2021)
- [Inspecting the Geographical Representativeness of Images from Text-to-Image Models](https://mlsanity.com/paper/2305.11080/) (2023)
- [Finding and Fixing Spurious Patterns with Explanations](https://mlsanity.com/paper/2106.02112/) (2021)
- [Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization](https://mlsanity.com/paper/2306.09264/) (2023)
- [Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models](https://mlsanity.com/paper/2207.01056/) (2022)
- [FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization](https://mlsanity.com/paper/2210.14562/) (2022)
- [FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification](https://mlsanity.com/paper/2407.08813/) (2024)
- [Information-Theoretic Bias Reduction via Causal View of Spurious Correlation](https://mlsanity.com/paper/2201.03121/) (2022)
- [FairVision: Equitable Deep Learning for Eye Disease Screening via Fair Identity Scaling](https://mlsanity.com/paper/2310.02492/) (2023)
- [Improving Fairness in Image Classification via Sketching](https://mlsanity.com/paper/2211.00168/) (2022)
- [Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing](https://mlsanity.com/paper/2108.12510/) (2021)
- [Fairness-aware Vision Transformer via Debiased Self-Attention](https://mlsanity.com/paper/2301.13803/) (2023)
- [A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models](https://mlsanity.com/paper/2401.03695/) (2024)
- [Exploring Empty Spaces: Human-in-the-Loop Data Augmentation](https://mlsanity.com/paper/2410.01088/) (2024)
- [Fairness and Sequential Decision Making: Limits, Lessons, and Opportunities](https://mlsanity.com/paper/2301.05753/) (2023)
- [FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling](https://mlsanity.com/paper/2311.02189/) (2023)
- [Unsupervised Search for Ethnic Minorities' Medical Segmentation Training Set](https://mlsanity.com/paper/2501.02442/) (2025)
- [EdgeMixup: Improving Fairness for Skin Disease Classification and Segmentation](https://mlsanity.com/paper/2202.13883/) (2022)
- [Stubborn Lexical Bias in Data and Models](https://mlsanity.com/paper/2306.02190/) (2023)
- [Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias](https://mlsanity.com/paper/2202.10582/) (2022)
- [On the Origins of Sampling Bias: Implications on Fairness Measurement and Mitigation](https://mlsanity.com/paper/2503.17956/) (2025)
- [Benign Adversarial Attack: Tricking Models for Goodness](https://mlsanity.com/paper/2107.11986/) (2021)
- [Shedding light on underrepresentation and Sampling Bias in machine learning](https://mlsanity.com/paper/2306.05068/) (2023)
- [Utilizing Adversarial Examples for Bias Mitigation and Accuracy Enhancement](https://mlsanity.com/paper/2404.11819/) (2024)
- [FaceSaliencyAug: Mitigating Geographic, Gender and Stereotypical Biases via Saliency-Based Data Augmentation](https://mlsanity.com/paper/2410.14070/) (2024)
- [Saliency-Based diversity and fairness Metric and FaceKeepOriginalAugment: A Novel Approach for Enhancing Fairness and Diversity](https://mlsanity.com/paper/2411.00831/) (2024)
- [Mitigating Group-Level Fairness Disparities in Federated Visual Language Models](https://mlsanity.com/paper/2505.01851/) (2025)
- [Fair Classification by Direct Intervention on Operating Characteristics](https://mlsanity.com/paper/2509.25481/) (2025)

## Abstract (arXiv)

Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data analysis on facial attribute recognition demonstrates (1) the attribution of model bias from imbalanced training data distribution and (2) the potential of adversarial examples in balancing data distribution. We are thus motivated to employ adversarial example to augment the training data for visual debiasing. Specifically, to ensure the adversarial generalization as well as cross-task transferability, we propose to couple the operations of target task classifier training, bias task classifier training, and adversarial example generation. The generated adversarial examples supplement the target task training dataset via balancing the distribution over bias variables in an online fashion. Results on simulated and real-world debiasing experiments demonstrate the effectiveness of the proposed solution in simultaneously improving model accuracy and fairness. Preliminary experiment on few-shot learning further shows the potential of adversarial attack-based pseudo sample generation as alternative solution to make up for the training data lackage.