# Identifying Bias in AI using Simulation

arXiv: https://arxiv.org/abs/1810.00471 · HTML: https://mlsanity.com/paper/1810.00471/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2018.

## Built on by (most cited first, 6 of 6)

- [SCAMPS: Synthetics for Camera Measurement of Physiological Signals](https://mlsanity.com/paper/2206.04197/) (2022)
- [Latent Space Smoothing for Individually Fair Representations](https://mlsanity.com/paper/2111.13650/) (2021)
- [Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement](https://mlsanity.com/paper/2303.12059/) (2023)
- [Synthetic Data for Multi-Parameter Camera-Based Physiological Sensing](https://mlsanity.com/paper/2110.04902/) (2021)
- [Detecting discriminatory risk through data annotation based on Bayesian inferences](https://mlsanity.com/paper/2101.11358/) (2021)
- [Causal effect of racial bias in data and machine learning algorithms on user persuasiveness & discriminatory decision making: An Empirical Study](https://mlsanity.com/paper/2202.00471/) (2022)

## Abstract (arXiv)

Machine learned models exhibit bias, often because the datasets used to train them are biased. This presents a serious problem for the deployment of such technology, as the resulting models might perform poorly on populations that are minorities within the training set and ultimately present higher risks to them. We propose to use high-fidelity computer simulations to interrogate and diagnose biases within ML classifiers. We present a framework that leverages Bayesian parameter search to efficiently characterize the high dimensional feature space and more quickly identify weakness in performance. We apply our approach to an example domain, face detection, and show that it can be used to help identify demographic biases in commercial face application programming interfaces (APIs).