# LUCID-GAN: Conditional Generative Models to Locate Unfairness

arXiv: https://arxiv.org/abs/2307.15466 · HTML: https://mlsanity.com/paper/2307.15466/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 53 references that are in the map.
- First posted on arXiv 28 Jul 2023.

## Builds on (most cited first, 28 of 28)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices](https://mlsanity.com/paper/1906.09208/) (2019)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [Fairness in Machine Learning: Lessons from Political Philosophy](https://mlsanity.com/paper/1712.03586/) (2017)
- [On the Apparent Conflict Between Individual and Group Fairness](https://mlsanity.com/paper/1912.06883/) (2019)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [PacGAN: The power of two samples in generative adversarial networks](https://mlsanity.com/paper/1712.04086/) (2017)
- [Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI](https://mlsanity.com/paper/2005.05906/) (2020)
- [Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learning](https://mlsanity.com/paper/2008.09202/) (2020)
- [The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations](https://mlsanity.com/paper/2205.03295/) (2022)
- [De-biasing "bias" measurement](https://mlsanity.com/paper/2205.05770/) (2022)
- [Simplicity Creates Inequity: Implications for Fairness, Stereotypes, and Interpretability](https://mlsanity.com/paper/1809.04578/) (2018)
- [LUCID: Exposing Algorithmic Bias through Inverse Design](https://mlsanity.com/paper/2208.12786/) (2022)

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

- [Decision-centric fairness: Evaluation and optimization for resource allocation problems](https://mlsanity.com/paper/2504.20642/) (2025)

## Abstract (arXiv)

Most group fairness notions detect unethical biases by computing statistical parity metrics on a model's output. However, this approach suffers from several shortcomings, such as philosophical disagreement, mutual incompatibility, and lack of interpretability. These shortcomings have spurred the research on complementary bias detection methods that offer additional transparency into the sources of discrimination and are agnostic towards an a priori decision on the definition of fairness and choice of protected features. A recent proposal in this direction is LUCID (Locating Unfairness through Canonical Inverse Design), where canonical sets are generated by performing gradient descent on the input space, revealing a model's desired input given a preferred output. This information about the model's mechanisms, i.e., which feature values are essential to obtain specific outputs, allows exposing potential unethical biases in its internal logic. Here, we present LUCID-GAN, which generates canonical inputs via a conditional generative model instead of gradient-based inverse design. LUCID-GAN has several benefits, including that it applies to non-differentiable models, ensures that canonical sets consist of realistic inputs, and allows to assess proxy and intersectional discrimination. We empirically evaluate LUCID-GAN on the UCI Adult and COMPAS data sets and show that it allows for detecting unethical biases in black-box models without requiring access to the training data.