# UnbiasedNets: A Dataset Diversification Framework for Robustness Bias Alleviation in Neural Networks

arXiv: https://arxiv.org/abs/2302.12538 · HTML: https://mlsanity.com/paper/2302.12538/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 64 references that are in the map.
- First posted on arXiv 24 Feb 2023.

## Builds on (most cited first, 27 of 27)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning](https://mlsanity.com/paper/1609.06570/) (2016)
- [Adversarial Filters of Dataset Biases](https://mlsanity.com/paper/2002.04108/) (2020)
- [REPAIR: Removing Representation Bias by Dataset Resampling](https://mlsanity.com/paper/1904.07911/) (2019)
- [Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems](https://mlsanity.com/paper/1907.10456/) (2019)
- [To be Robust or to be Fair: Towards Fairness in Adversarial Training](https://mlsanity.com/paper/2010.06121/) (2020)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)
- [Learning from others' mistakes: Avoiding dataset biases without modeling them](https://mlsanity.com/paper/2012.01300/) (2020)
- [Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies](https://mlsanity.com/paper/2010.10802/) (2020)
- [Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning](https://mlsanity.com/paper/2006.12621/) (2020)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy](https://mlsanity.com/paper/2010.13365/) (2020)
- [Parallelization Techniques for Verifying Neural Networks](https://mlsanity.com/paper/2004.08440/) (2020)
- [Analysis and Applications of Class-wise Robustness in Adversarial Training](https://mlsanity.com/paper/2105.14240/) (2021)
- [Intra-Processing Methods for Debiasing Neural Networks](https://mlsanity.com/paper/2006.08564/) (2020)
- [Fair SA: Sensitivity Analysis for Fairness in Face Recognition](https://mlsanity.com/paper/2202.03586/) (2022)
- [FANNet: Formal Analysis of Noise Tolerance, Training Bias and Input Sensitivity in Neural Networks](https://mlsanity.com/paper/1912.01978/) (2019)
- [Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems](https://mlsanity.com/paper/2205.02604/) (2022)
- [Improve Model Generalization and Robustness to Dataset Bias with Bias-regularized Learning and Domain-guided Augmentation](https://mlsanity.com/paper/1910.06745/) (2019)

## Built on by (most cited first, 2 of 2)

- [It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness](https://mlsanity.com/paper/2303.09767/) (2023)
- [Poster: Link between Bias, Node Sensitivity and Long-Tail Distribution in trained DNNs](https://mlsanity.com/paper/2303.16589/) (2023)

## Abstract (arXiv)

Performance of trained neural network (NN) models, in terms of testing accuracy, has improved remarkably over the past several years, especially with the advent of deep learning. However, even the most accurate NNs can be biased toward a specific output classification due to the inherent bias in the available training datasets, which may propagate to the real-world implementations. This paper deals with the robustness bias, i.e., the bias exhibited by the trained NN by having a significantly large robustness to noise for a certain output class, as compared to the remaining output classes. The bias is shown to result from imbalanced datasets, i.e., the datasets where all output classes are not equally represented. Towards this, we propose the UnbiasedNets framework, which leverages K-means clustering and the NN's noise tolerance to diversify the given training dataset, even from relatively smaller datasets. This generates balanced datasets and reduces the bias within the datasets themselves. To the best of our knowledge, this is the first framework catering to the robustness bias problem in NNs. We use real-world datasets to demonstrate the efficacy of the UnbiasedNets for data diversification, in case of both binary and multi-label classifiers. The results are compared to well-known tools aimed at generating balanced datasets, and illustrate how existing works have limited success while addressing the robustness bias. In contrast, UnbiasedNets provides a notable improvement over existing works, while even reducing the robustness bias significantly in some cases, as observed by comparing the NNs trained on the diversified and original datasets.