mlsanityData to 14 Oct 2026

NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification

arXiv 2112.13214 ↗First posted 25 Dec 2021cs.LG cs.AIcited by 42

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have demonstrated their outperformance in various domains. However, it raises a social concern whether DNNs can produce reliable and fair decisions especially when they are applied to sensitive domains involving valuable resource allocation, such as education, loan, and employment. It is crucial to conduct fairness testing before DNNs are reliably deployed to such sensitive domains, i.e., generating as many instances as possible to uncover fairness violations. However, the existing testing methods are still limited from three aspects: interpretability, performance, and generalizability. To overcome the challenges, we propose NeuronFair, a new DNN fairness testing framework that differs from previous work in several key aspects: (1) interpretable - it quantitatively interprets DNNs' fairness violations for the biased decision; (2) effective - it uses the interpretation results to guide the generation of more diverse instances in less time; (3) generic - it can handle both structured and unstructured data. Extensive evaluations across 7 datasets and the corresponding DNNs demonstrate NeuronFair's superior performance. For instance, on structured datasets, it generates much more instances (~x5.84) and saves more time (with an average speedup of 534.56%) compared with the state-of-the-art methods. Besides, the instances of NeuronFair can also be leveraged to improve the fairness of the biased DNNs, which helps build more fair and trustworthy deep learning systems.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 32 of its 65 references that are in the map. First posted on arXiv 25 Dec 2021.

Builds on

32 of 65 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  8. 2017Counterfactual Fairnesscited by 804
  9. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  10. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  11. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 381
  12. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
20 more
  1. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
  2. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  3. 2017Fairness Testing: Testing Software for Discriminationcited by 126
  4. 2020Fair Attribute Classification through Latent Space De-biasingcited by 125
  5. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  6. 2018Automated Directed Fairness Testingcited by 78
  7. 2020Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairnesscited by 52
  8. 2019FlipTest: Fairness Testing via Optimal Transportcited by 51
  9. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  10. 2021DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injectioncited by 44
  11. 2019SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systemscited by 34
  12. 2015Exploring the Space of Adversarial Imagescited by 28
  13. 2018Automated Test Generation to Detect Individual Discrimination in AI Modelscited by 21
  14. 2021Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Appscited by 19
  15. 2016Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Modelscited by 12
  16. 2020Deep Learning & Software Engineering: State of Research and Future Directionscited by 9
  17. 2018Complex Network Classification with Convolutional Neural Networkcited by 6
  18. 2021Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Modelscited by 6
  19. 2021Automated Performance Testing Based on Active Deep Learningcited by 4
  20. 2021On Adaptive Fairness in Software Systemscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 11; 2024: 7; 2025: 11; 2026: 6.

42 papers.

Sort:

By area:

  1. 2024GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probingcited by 31
  2. 2022A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifierscited by 30
  3. 2023Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testingcited by 23
  4. 2022Fairify: Fairness Verification of Neural Networkscited by 22
  5. 2022Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifscited by 19
  6. 2022Towards Understanding Fairness and its Composition in Ensemble Machine Learningcited by 17
  7. 2023A Critical Survey on Fairness Benefits of Explainable AIcited by 16
  8. 2023Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinkingcited by 14
  9. 2023FAIRER: Fairness as Decision Rationale Alignmentcited by 12
  10. 2024NeuFair: Neural Network Fairness Repair with Dropoutcited by 11
  11. 2024Fairness Testing of Large Language Models in Role-Playingcited by 11
  12. 2023Information-Theoretic Testing and Debugging of Fairness Defects in Deep Neural Networkscited by 10
30 more
  1. 2022"Is your explanation stable?": A Robustness Evaluation Framework for Feature Attributioncited by 7
  2. 2025FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledgecited by 5
  3. 2023CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Spacecited by 4
  4. 2024FairQuant: Certifying and Quantifying Fairness of Deep Neural Networkscited by 4
  5. 2024MAFT: Efficient Model-Agnostic Fairness Testing for Deep Neural Networks via Zero-Order Gradient Searchcited by 4
  6. 2024Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Softwarecited by 3
  7. 2025FairSense: Long-Term Fairness Analysis of ML-Enabled Systemscited by 3
  8. 2022Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-modal Fake News Detectioncited by 2
  9. 2022Enhanced Fairness Testing via Generating Effective Initial Individual Discriminatory Instancescited by 2
  10. 2025Fairness Testing through Extreme Value Theorycited by 2
  11. 2023CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinementcited by 1
  12. 2023DREAM: Debugging and Repairing AutoML Pipelinescited by 1
  13. 2025Software Fairness Dilemma: Is Bias Mitigation a Zero-Sum Game?cited by 1
  14. 2025Correct-By-Construction: Certified Individual Fairness through Neural Network Trainingcited by 1
  15. 2025Causally Perturbed Fairness Testingcited by 1
  16. 2025Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violationscited by 1
  17. 2026Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generationcited by 1
  18. 2023An Automata-Theoretic Approach to Synthesizing Binarized Neural Networkscited by 0
  19. 2023Fairness Improvement with Multiple Protected Attributes: How Far Are We?cited by 0
  20. 2023Search-Based Fairness Testing: An Overviewcited by 0
  21. 2024Contexts Matter: An Empirical Study on Contextual Influence in Fairness Testing for Deep Learning Systemscited by 0
  22. 2025Testing Individual Fairness in Graph Neural Networkscited by 0
  23. 2025FairFLRep: Fairness aware fault localization and repair of Deep Neural Networkscited by 0
  24. 2025CAF'E: Causal Black-Box Testing of Machine Unlearningcited by 0
  25. 2025PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linkingcited by 0
  26. 2026Shapley-Guided Neural Repair Approach via Derivative-Free Optimizationcited by 0
  27. 2026Provable Fairness Repair for Deep Neural Networkscited by 0
  28. 2026Demystifying the Optimal Fair Classifier in Multi-Class Classificationcited by 0
  29. 2026Test Case Prioritization for DNNs via Neural Collapse Instabilitycited by 0
  30. 2026Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugscited by 0