mlsanityData to 14 Oct 2026

Perfectly Parallel Fairness Certification of Neural Networks

arXiv 1912.02499 ↗First posted 5 Dec 2019cs.PL cs.CY cs.LGcited by 42

Not on the map. Why?

Abstract (arXiv)

Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case reinforce, bias of the training data. The development of tools and techniques for certifying fairness of these models or describing their biased behavior is, therefore, critical. In this paper, we propose a perfectly parallel static analysis for certifying causal fairness of feed-forward neural networks used for classification of tabular data. When certification succeeds, our approach provides definite guarantees, otherwise, it describes and quantifies the biased behavior. We design the analysis to be sound, in practice also exact, and configurable in terms of scalability and precision, thereby enabling pay-as-you-go certification. We implement our approach in an open-source tool and demonstrate its effectiveness on models trained with popular datasets.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 14; 2023: 6; 2024: 7; 2025: 5; 2026: 4.

42 papers.

Sort:

  1. 2021Fair Normalizing Flowscited by 38
  2. 2021A Review of Formal Methods applied to Machine Learningcited by 33
  3. 2022An Abstraction-Refinement Approach to Verifying Convolutional Neural Networkscited by 24
  4. 2022Individual Fairness Guarantees for Neural Networkscited by 23
  5. 2022Fairify: Fairness Verification of Neural Networkscited by 22
  6. 2021Neural Network Repair with Reachability Analysiscited by 19
  7. 2022Scalable Verification of GNN-based Job Schedulerscited by 19
  8. 2021Latent Space Smoothing for Individually Fair Representationscited by 18
  9. 2022Verification-Aided Deep Ensemble Selectioncited by 18
  10. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  11. 2024FairProof : Confidential and Certifiable Fairness for Neural Networkscited by 13
  12. 2022Certifying Some Distributional Fairness with Subpopulation Decompositioncited by 11
30 more
  1. 2023Verifying Generalization in Deep Learningcited by 11
  2. 2022CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustnesscited by 9
  3. 2024Neural Network Verification with PyRATcited by 9
  4. 2022Provable Fairness for Neural Network Models using Formal Verificationcited by 6
  5. 2022Specifying and Testing k-Safety Properties for Machine-Learning Modelscited by 5
  6. 2022Explainable Global Fairness Verification of Tree-Based Classifierscited by 5
  7. 2021Fair Training of Decision Tree Classifierscited by 4
  8. 2021Self-Correcting Neural Networks For Safe Classificationcited by 4
  9. 2022FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networkscited by 4
  10. 2023Precise and Generalized Robustness Certification for Neural Networkscited by 4
  11. 2024Solving Probabilistic Verification Problems of Neural Networks using Branch and Boundcited by 4
  12. 2024FairQuant: Certifying and Quantifying Fairness of Deep Neural Networkscited by 4
  13. 2023DelBugV: Delta-Debugging Neural Network Verifierscited by 3
  14. 2025Monitoring Robustness and Individual Fairnesscited by 3
  15. 2024Verifying the Generalization of Deep Learning to Out-of-Distribution Domainscited by 2
  16. 2022Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbationscited by 1
  17. 2024Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deploymentcited by 1
  18. 2025Correct-By-Construction: Certified Individual Fairness through Neural Network Trainingcited by 1
  19. 2025Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violationscited by 1
  20. 2026Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generationcited by 1
  21. 2022Abstract Interpretation-Based Feature Importance for SVMscited by 0
  22. 2023Evaluating robustness of support vector machines with the Lagrangian dual approachcited by 0
  23. 2023Verifying Global Neural Network Specifications using Hyperpropertiescited by 0
  24. 2023Verification of Neural Networks Local Differential Classification Privacycited by 0
  25. 2024Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretationcited by 0
  26. 2025Language Models That Walk the Talk: A Framework for Formal Fairness Certificatescited by 0
  27. 2025The CAISAR Platform: Extending the Reach of Machine Learning Specification and Verificationcited by 0
  28. 2026From Specification to Architecture: A Theory Compiler for Knowledge-Guided Machine Learningcited by 0
  29. 2026Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugscited by 0
  30. 2026NNV3: Expanding Neural Network Verification to New Architectures and Domainscited by 0