mlsanityData to 7 Oct 2026

FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks

arXiv 2409.03220 ↗First posted 5 Sep 2024cs.LG cs.SEcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose a method for formally certifying and quantifying individual fairness of deep neural networks (DNN). Individual fairness guarantees that any two individuals who are identical except for a legally protected attribute (e.g., gender or race) receive the same treatment. While there are existing techniques that provide such a guarantee, they tend to suffer from lack of scalability or accuracy as the size and input dimension of the DNN increase. Our method overcomes this limitation by applying abstraction to a symbolic interval based analysis of the DNN followed by iterative refinement guided by the fairness property. Furthermore, our method lifts the symbolic interval based analysis from conventional qualitative certification to quantitative certification, by computing the percentage of individuals whose classification outputs are provably fair, instead of merely deciding if the DNN is fair. We have implemented our method and evaluated it on deep neural networks trained on four popular fairness research datasets. The experimental results show that our method is not only more accurate than state-of-the-art techniques but also several orders-of-magnitude faster.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 65 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

32 of 65 references.

References · 32

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2017Counterfactual Fairnesscited by 802
  3. 2014Certifying and removing disparate impactcited by 715
  4. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  5. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  6. 2018Formal Security Analysis of Neural Networks using Symbolic Intervalscited by 185
  7. 2018Efficient Formal Safety Analysis of Neural Networkscited by 165
  8. 2021A survey on datasets for fairness-aware machine learningcited by 157
  9. 2019Branch and Bound for Piecewise Linear Neural Network Verificationcited by 138
  10. 2017Fairness Testing: Testing Software for Discriminationcited by 123
  11. 2016Measuring Neural Net Robustness with Constraintscited by 90
  12. 2018Automated Directed Fairness Testingcited by 77
20 more
  1. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  2. 2020Learning Certified Individually Fair Representationscited by 69
  3. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  4. 2018Probabilistic Verification of Fairness Properties via Concentrationcited by 45
  5. 2020Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policycited by 44
  6. 2019Perfectly Parallel Fairness Certification of Neural Networkscited by 42
  7. 2020In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Predictioncited by 42
  8. 2021NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identificationcited by 42
  9. 2020Improving Neural Network Verification through Spurious Region Guided Refinementcited by 30
  10. 2020ReluDiff: Differential Verification of Deep Neural Networkscited by 29
  11. 2022Individual Fairness Guarantees for Neural Networkscited by 23
  12. 2020NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximationcited by 22
  13. 2022FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neuronscited by 20
  14. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  15. 2022On Neural Network Equivalence Checking using SMT Solverscited by 10
  16. 2023Information-Theoretic Testing and Debugging of Fairness Defects in Deep Neural Networkscited by 10
  17. 2021BeFair: Addressing Fairness in the Banking Sectorcited by 8
  18. 2023Certifying the Fairness of KNN in the Presence of Dataset Biascited by 7
  19. 2019Mitigating Power Side Channels during Compilationcited by 4
  20. 2021Data-Driven Synthesis of Provably Sound Side Channel Analysescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violationscited by 1
  2. 2026Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generationcited by 1
  3. 2026Quantifying Sensitivity for Tree Ensembles: A symbolic and compositional approachcited by 0
  4. 2026Provable Fairness Repair for Deep Neural Networkscited by 0