# Automated Test Generation to Detect Individual Discrimination in AI Models

arXiv: https://arxiv.org/abs/1809.03260 · HTML: https://mlsanity.com/paper/1809.03260/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2018.

## Built on by (most cited first, 21 of 21)

- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification](https://mlsanity.com/paper/2112.13214/) (2021)
- [FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons](https://mlsanity.com/paper/2204.02567/) (2022)
- [Probabilistic Verification of Neural Networks Against Group Fairness](https://mlsanity.com/paper/2107.08362/) (2021)
- [A Survey on AI Assurance](https://mlsanity.com/paper/2111.07505/) (2021)
- [Information-Theoretic Testing and Debugging of Fairness Defects in Deep Neural Networks](https://mlsanity.com/paper/2304.04199/) (2023)
- [Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Difference](https://mlsanity.com/paper/2302.11944/) (2023)
- [TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination](https://mlsanity.com/paper/2208.11321/) (2022)
- [FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks](https://mlsanity.com/paper/2206.00553/) (2022)
- [MAFT: Efficient Model-Agnostic Fairness Testing for Deep Neural Networks via Zero-Order Gradient Search](https://mlsanity.com/paper/2412.20086/) (2024)
- [Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems](https://mlsanity.com/paper/2408.15550/) (2024)
- [Enhanced Fairness Testing via Generating Effective Initial Individual Discriminatory Instances](https://mlsanity.com/paper/2209.08321/) (2022)
- [Fairness Testing through Extreme Value Theory](https://mlsanity.com/paper/2501.11597/) (2025)
- [Counterfactual Situation Testing: From Single to Multidimensional Discrimination](https://mlsanity.com/paper/2502.01267/) (2025)
- [Informative Post-Hoc Explanations Only Exist for Simple Functions](https://mlsanity.com/paper/2508.11441/) (2025)
- [fAux: Testing Individual Fairness via Gradient Alignment](https://mlsanity.com/paper/2210.06288/) (2022)
- [CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement](https://mlsanity.com/paper/2304.04222/) (2023)
- [Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations](https://mlsanity.com/paper/2512.23769/) (2025)
- [Efficient DNN-Powered Software with Fair Sparse Models](https://mlsanity.com/paper/2407.02805/) (2024)
- [We Need Explanation Cards to Connect Explanation Algorithms to the Real World](https://mlsanity.com/paper/2606.16786/) (2026)
- [Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs](https://mlsanity.com/paper/2608.26209/) (2026)

## Abstract (arXiv)

Dependability on AI models is of utmost importance to ensure full acceptance of the AI systems. One of the key aspects of the dependable AI system is to ensure that all its decisions are fair and not biased towards any individual. In this paper, we address the problem of detecting whether a model has an individual discrimination. Such a discrimination exists when two individuals who differ only in the values of their protected attributes (such as, gender/race) while the values of their non-protected ones are exactly the same, get different decisions. Measuring individual discrimination requires an exhaustive testing, which is infeasible for a non-trivial system. In this paper, we present an automated technique to generate test inputs, which is geared towards finding individual discrimination. Our technique combines the well-known technique called symbolic execution along with the local explainability for generation of effective test cases. Our experimental results clearly demonstrate that our technique produces 3.72 times more successful test cases than the existing state-of-the-art across all our chosen benchmarks.