# Adversarial Sampling for Fairness Testing in Deep Neural Network

arXiv: https://arxiv.org/abs/2303.02874 · HTML: https://mlsanity.com/paper/2303.02874/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 6 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching](https://mlsanity.com/paper/2009.02276/) (2020)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [To be Robust or to be Fair: Towards Fairness in Adversarial Training](https://mlsanity.com/paper/2010.06121/) (2020)
- [Fairness Testing: Testing Software for Discrimination](https://mlsanity.com/paper/1709.03221/) (2017)
- [Adversarial Machine Learning -- Industry Perspectives](https://mlsanity.com/paper/2002.05646/) (2020)
- [Automated Directed Fairness Testing](https://mlsanity.com/paper/1807.00468/) (2018)
- [APE-GAN: Adversarial Perturbation Elimination with GAN](https://mlsanity.com/paper/1707.05474/) (2017)
- [Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)](https://mlsanity.com/paper/2008.00742/) (2020)
- [Probabilistic Verification of Fairness Properties via Concentration](https://mlsanity.com/paper/1812.02573/) (2018)
- [Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling](https://mlsanity.com/paper/2107.08176/) (2021)
- [Information Laundering for Model Privacy](https://mlsanity.com/paper/2009.06112/) (2020)
- [Bypassing Feature Squeezing by Increasing Adversary Strength](https://mlsanity.com/paper/1803.09868/) (2018)

## Built on by (most cited first, 5 of 5)

- [Encoder-Decoder Based Long Short-Term Memory (LSTM) Model for Video Captioning](https://mlsanity.com/paper/2401.02052/) (2023)
- [Deep Learning-Based Speech and Vision Synthesis to Improve Phishing Attack Detection through a Multi-layer Adaptive Framework](https://mlsanity.com/paper/2402.17249/) (2024)
- [An Investigation into the Performances of the State-of-the-art Machine Learning Approaches for Various Cyber-attack Detection: A Survey](https://mlsanity.com/paper/2402.17045/) (2024)
- [An investigation into the performances of the Current state-of-the-art Naive Bayes, Non-Bayesian and Deep Learning Based Classifier for Phishing Detection: A Survey](https://mlsanity.com/paper/2411.16751/) (2024)
- [MAD-OOD: A Deep Learning Cluster-Driven Framework for an Out-of-Distribution Malware Detection and Classification](https://mlsanity.com/paper/2512.17594/) (2025)

## Abstract (arXiv)

In this research, we focus on the usage of adversarial sampling to test for the fairness in the prediction of deep neural network model across different classes of image in a given dataset. While several framework had been proposed to ensure robustness of machine learning model against adversarial attack, some of which includes adversarial training algorithm. There is still the pitfall that adversarial training algorithm tends to cause disparity in accuracy and robustness among different group. Our research is aimed at using adversarial sampling to test for fairness in the prediction of deep neural network model across different classes or categories of image in a given dataset. We successfully demonstrated a new method of ensuring fairness across various group of input in deep neural network classifier. We trained our neural network model on the original image, and without training our model on the perturbed or attacked image. When we feed the adversarial samplings to our model, it was able to predict the original category/ class of the image the adversarial sample belongs to. We also introduced and used the separation of concern concept from software engineering whereby there is an additional standalone filter layer that filters perturbed image by heavily removing the noise or attack before automatically passing it to the network for classification, we were able to have accuracy of 93.3%. Cifar-10 dataset have ten categories of dataset, and so, in order to account for fairness, we applied our hypothesis across each categories of dataset and were able to get a consistent result and accuracy.