mlsanityData to 7 Oct 2026

Probabilistic Verification of Fairness Properties via Concentration

arXiv 1812.02573 ↗First posted 2 Dec 2018cs.AIcited by 45

Not on the map. Why?

Abstract (arXiv)

As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities. We design a scalable algorithm for verifying fairness specifications. Our algorithm obtains strong correctness guarantees based on adaptive concentration inequalities; such inequalities enable our algorithm to adaptively take samples until it has enough data to make a decision. We implement our algorithm in a tool called VeriFair, and show that it scales to large machine learning models, including a deep recurrent neural network that is more than five orders of magnitude larger than the largest previously-verified neural network. While our technique only gives probabilistic guarantees due to the use of random samples, we show that we can choose the probability of error to be extremely small.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 12; 2023: 6; 2024: 6; 2025: 9; 2026: 4.

45 papers.

Sort:

By area:

  1. 2021Trustworthy AI: A Computational Perspectivecited by 93
  2. 2022Causality-based Neural Network Repaircited by 44
  3. 2021Fair Normalizing Flowscited by 38
  4. 2022Individual Fairness Guarantees for Neural Networkscited by 23
  5. 2022Fairify: Fairness Verification of Neural Networkscited by 22
  6. 2021Latent Space Smoothing for Individually Fair Representationscited by 18
  7. 2021Probabilistic Verification of Neural Networks Against Group Fairnesscited by 17
  8. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  9. 2021Algorithmic Fairness Verification with Graphical Modelscited by 16
  10. 2021Automatic Fairness Testing of Neural Classifiers through Adversarial Samplingcited by 14
  11. 2024FairProof : Confidential and Certifiable Fairness for Neural Networkscited by 13
  12. 2022Certifying Some Distributional Fairness with Subpopulation Decompositioncited by 11
33 more
  1. 2024Certifying Counterfactual Bias in LLMscited by 9
  2. 2023Monitoring Algorithmic Fairnesscited by 8
  3. 2022Verifying Fairness in Quantum Machine Learningcited by 7
  4. 2023Certifying the Fairness of KNN in the Presence of Dataset Biascited by 7
  5. 2023Monitoring Algorithmic Fairness under Partial Observationscited by 7
  6. 2021Fairness Testing of Deep Image Classification with Adequacy Metricscited by 6
  7. 2022Provable Fairness for Neural Network Models using Formal Verificationcited by 6
  8. 2022Specifying and Testing k-Safety Properties for Machine-Learning Modelscited by 5
  9. 2022Explainable Global Fairness Verification of Tree-Based Classifierscited by 5
  10. 2023Adversarial Sampling for Fairness Testing in Deep Neural Networkcited by 5
  11. 2025Stream-Based Monitoring of Algorithmic Fairnesscited by 5
  12. 2022FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networkscited by 4
  13. 2024Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Predictioncited by 4
  14. 2024Solving Probabilistic Verification Problems of Neural Networks using Branch and Boundcited by 4
  15. 2024FairQuant: Certifying and Quantifying Fairness of Deep Neural Networkscited by 4
  16. 2022Certifying Fairness of Probabilistic Circuitscited by 3
  17. 2025FairSense: Long-Term Fairness Analysis of ML-Enabled Systemscited by 3
  18. 2023A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximationcited by 2
  19. 2025Correct-By-Construction: Certified Individual Fairness through Neural Network Trainingcited by 1
  20. 2026Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generationcited by 1
  21. 2021Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketchingcited by 0
  22. 2022DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximationcited by 0
  23. 2023Verification of Neural Networks Local Differential Classification Privacycited by 0
  24. 2024Probabilistic ML Verification via Weighted Model Integrationcited by 0
  25. 2025FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentationcited by 0
  26. 2025Language Models That Walk the Talk: A Framework for Formal Fairness Certificatescited by 0
  27. 2025Monitoring of Static Fairnesscited by 0
  28. 2025Algorithmic Fairness: A Runtime Perspectivecited by 0
  29. 2025The Fair Game: Auditing & Debiasing AI Algorithms Over Timecited by 0
  30. 2025Wasserstein projection distance for fairness testing of regression modelscited by 0
  31. 2026Shapley-Guided Neural Repair Approach via Derivative-Free Optimizationcited by 0
  32. 2026Energy Shields for Fairnesscited by 0
  33. 2026Beyond Binary: Continuous State Optimization with Graph-Structured Objectivescited by 0