mlsanityData to 14 Oct 2026

FairProof : Confidential and Certifiable Fairness for Neural Networks

arXiv 2402.12572 ↗First posted 19 Feb 2024cs.LG cs.AI cs.CRcited by 13

Not on the map. Why?

Abstract (arXiv)

Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models in the minds of consumers, who are often at the receiving end of model predictions. To this end, we propose name -- a system that uses Zero-Knowledge Proofs (a cryptographic primitive) to publicly verify the fairness of a model, while maintaining confidentiality. We also propose a fairness certification algorithm for fully-connected neural networks which is befitting to ZKPs and is used in this system. We implement name in Gnark and demonstrate empirically that our system is practically feasible. Code is available at https://github.com/infinite-pursuits/FairProof.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 29 of its 65 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

29 of 65 references.

References · 29

  1. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  2. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  3. 2017Bounding and Counting Linear Regions of Deep Neural Networkscited by 161
  4. 2019Deep ReLU Networks Have Surprisingly Few Activation Patternscited by 161
  5. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126
  6. 2014Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discriminationcited by 83
  7. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  8. 2020Learning Certified Individually Fair Representationscited by 69
  9. 2018Provable Robustness of ReLU networks via Maximization of Linear Regionscited by 51
  10. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  11. 2018Probabilistic Verification of Fairness Properties via Concentrationcited by 45
  12. 2019Perfectly Parallel Fairness Certification of Neural Networkscited by 42
17 more
  1. 2018Blind Justice: Fairness with Encrypted Sensitive Attributescited by 41
  2. 2022Scaling up Trustless DNN Inference with Zero-Knowledge Proofscited by 31
  3. 2019VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a Servicecited by 28
  4. 2019Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopescited by 25
  5. 2020Justicia: A Stochastic SAT Approach to Formally Verify Fairnesscited by 25
  6. 2022Individual Fairness Guarantees for Neural Networkscited by 23
  7. 2022Fairify: Fairness Verification of Neural Networkscited by 22
  8. 2022pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testingcited by 20
  9. 2020Individual Fairness Revisited: Transferring Techniques from Adversarial Robustnesscited by 17
  10. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  11. 2020Fairness in the Eyes of the Data: Certifying Machine-Learning Modelscited by 16
  12. 2019Faking Fairness via Stealthily Biased Samplingcited by 14
  13. 2021Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verificationcited by 13
  14. 2022Certifying Some Distributional Fairness with Subpopulation Decompositioncited by 11
  15. 2022Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivitycited by 8
  16. 2019Dissecting Deep Neural Networkscited by 7
  17. 2023Verifiable Fairness: Privacy-preserving Computation of Fairness for Machine Learning Systemscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 6.

13 papers.

Sort:

  1. 2024Secure and Confidential Certificates of Online Fairnesscited by 7
  2. 2025Robust ML Auditing using Prior Knowledgecited by 6
  3. 2025FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledgecited by 5
  4. 2025ExpProof : Operationalizing Explanations for Confidential Models with ZKPscited by 2
  5. 2025A Framework for Cryptographic Verifiability of End-to-End AI Pipelinescited by 2
  6. 2025Justified Evidence Collection for Argument-based AI Fairness Assurancecited by 2
  7. 2025Happiness as a Measure of Fairnesscited by 0
  8. 2026Robust Federated Learning via Byzantine Filtering over Encrypted Updatescited by 0
  9. 2026Certification of Machine Learning Models via Directional Sharpnesscited by 0
  10. 2026Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certificationcited by 0
  11. 2026ZK-SR117: A Chunked Zero-Knowledge Attestation Design for Aggregated Fair-Lending Metrics, with a Control Mapping toward Full SR 11-7 Coveragecited by 0
  12. 2026Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guaranteescited by 0
1 more
  1. 2026Bits Under ZK-LLM: Evaluating Zero-Knowledge-Friendly Quantization for Verifiable Private LLM Inferencecited by 0