# Causally Perturbed Fairness Testing

arXiv: https://arxiv.org/abs/2510.18719 · HTML: https://mlsanity.com/paper/2510.18719/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Fairness in Criminal Justice Risk Assessments: The State of the Art](https://mlsanity.com/paper/1703.09207/) (2017)
- [Fairness Testing: Testing Software for Discrimination](https://mlsanity.com/paper/1709.03221/) (2017)
- [On the Apparent Conflict Between Individual and Group Fairness](https://mlsanity.com/paper/1912.06883/) (2019)
- [Automated Directed Fairness Testing](https://mlsanity.com/paper/1807.00468/) (2018)
- [Fairness Testing: A Comprehensive Survey and Analysis of Trends](https://mlsanity.com/paper/2207.10223/) (2022)
- [Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness](https://mlsanity.com/paper/2005.12379/) (2020)
- [Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features](https://mlsanity.com/paper/2104.14537/) (2021)
- [NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification](https://mlsanity.com/paper/2112.13214/) (2021)
- [Personalized Counterfactual Fairness in Recommendation](https://mlsanity.com/paper/2105.09829/) (2021)
- [Multi-Objectivizing Software Configuration Tuning (for a single performance concern)](https://mlsanity.com/paper/2106.01331/) (2021)
- [Fairness-aware Configuration of Machine Learning Libraries](https://mlsanity.com/paper/2202.06196/) (2022)
- [Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing](https://mlsanity.com/paper/2305.11602/) (2023)
- [The Weights can be Harmful: Pareto Search versus Weighted Search in Multi-Objective Search-Based Software Engineering](https://mlsanity.com/paper/2202.03728/) (2022)
- [Adaptive Fairness Improvement Based on Causality Analysis](https://mlsanity.com/paper/2209.07190/) (2022)
- [Predicting Configuration Performance in Multiple Environments with Sequential Meta-learning](https://mlsanity.com/paper/2402.03183/) (2024)
- [Predicting Software Performance with Divide-and-Learn](https://mlsanity.com/paper/2306.06651/) (2023)
- [VerifyMed -- A blockchain platform for transparent trust in virtualized healthcare: Proof-of-concept](https://mlsanity.com/paper/2005.08804/) (2020)
- [Adapting Multi-objectivized Software Configuration Tuning](https://mlsanity.com/paper/2404.04744/) (2024)
- [Trade-offs between Group Fairness Metrics in Societal Resource Allocation](https://mlsanity.com/paper/2202.12334/) (2022)

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

- [Human-Machine Co-Boosted Bug Report Identification with Mutualistic Neural Active Learning](https://mlsanity.com/paper/2604.18862/) (2026)

## Abstract (arXiv)

To mitigate unfair and unethical discrimination over sensitive features (e.g., gender, age, or race), fairness testing plays an integral role in engineering systems that leverage AI models to handle tabular data. A key challenge therein is how to effectively reveal fairness bugs under an intractable sample size using perturbation. Much current work has been focusing on designing the test sample generators, ignoring the valuable knowledge about data characteristics that can help guide the perturbation and hence limiting their full potential. In this paper, we seek to bridge such a gap by proposing a generic framework of causally perturbed fairness testing, dubbed CausalFT. Through causal inference, the key idea of CausalFT is to extract the most directly and causally relevant non-sensitive feature to its sensitive counterpart, which can jointly influence the prediction of the label. Such a causal relationship is then seamlessly injected into the perturbation to guide a test sample generator. Unlike existing generator-level work, CausalFT serves as a higher-level framework that can be paired with diverse base generators. Extensive experiments on 1296 cases confirm that CausalFT can considerably improve arbitrary base generators in revealing fairness bugs over 93% of the cases with acceptable extra runtime overhead. Compared with a state-of-the-art approach that ranks the non-sensitive features solely based on correlation, CausalFT performs significantly better on 64% cases while being much more efficient. Further, CausalFT can better improve bias resilience in nearly all cases.