# Secure and Confidential Certificates of Online Fairness

arXiv: https://arxiv.org/abs/2410.02777 · HTML: https://mlsanity.com/paper/2410.02777/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 53 references that are in the map.
- First posted on arXiv 17 Sep 2024.

## Builds on (most cited first, 20 of 20)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Aequitas: A Bias and Fairness Audit Toolkit](https://mlsanity.com/paper/1811.05577/) (2018)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [50 Years of Test (Un)fairness: Lessons for Machine Learning](https://mlsanity.com/paper/1811.10104/) (2018)
- [Fairwashing: the risk of rationalization](https://mlsanity.com/paper/1901.09749/) (2019)
- [Mitigating Face Recognition Bias via Group Adaptive Classifier](https://mlsanity.com/paper/2006.07576/) (2020)
- [Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints](https://mlsanity.com/paper/1807.00028/) (2018)
- [zkLLM: Zero Knowledge Proofs for Large Language Models](https://mlsanity.com/paper/2404.16109/) (2024)
- [Verifying Individual Fairness in Machine Learning Models](https://mlsanity.com/paper/2006.11737/) (2020)
- [Blind Justice: Fairness with Encrypted Sensitive Attributes](https://mlsanity.com/paper/1806.03281/) (2018)
- [Fairness Transferability Subject to Bounded Distribution Shift](https://mlsanity.com/paper/2206.00129/) (2022)
- [FairLens: Auditing Black-box Clinical Decision Support Systems](https://mlsanity.com/paper/2011.04049/) (2020)
- [Ensuring Fairness under Prior Probability Shifts](https://mlsanity.com/paper/2005.03474/) (2020)
- [Fairness in the Eyes of the Data: Certifying Machine-Learning Models](https://mlsanity.com/paper/2009.01534/) (2020)
- [FairProof : Confidential and Certifiable Fairness for Neural Networks](https://mlsanity.com/paper/2402.12572/) (2024)
- [Verifiable Fairness: Privacy-preserving Computation of Fairness for Machine Learning Systems](https://mlsanity.com/paper/2309.06061/) (2023)
- [Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning](https://mlsanity.com/paper/2402.15780/) (2024)
- [PrivFair: a Library for Privacy-Preserving Fairness Auditing](https://mlsanity.com/paper/2202.04058/) (2022)
- [Having your Privacy Cake and Eating it Too: Platform-supported Auditing of Social Media Algorithms for Public Interest](https://mlsanity.com/paper/2207.08773/) (2022)

## Built on by (most cited first, 7 of 7)

- [TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks](https://mlsanity.com/paper/2504.19274/) (2025)
- [FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledge](https://mlsanity.com/paper/2505.07997/) (2025)
- [A Framework for Cryptographic Verifiability of End-to-End AI Pipelines](https://mlsanity.com/paper/2503.22573/) (2025)
- [Manipulation-Proof Oblivious Audits against Deceptive Model Providers](https://mlsanity.com/paper/2608.04365/) (2026)
- [Certification of Machine Learning Models via Directional Sharpness](https://mlsanity.com/paper/2606.25004/) (2026)
- [Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees](https://mlsanity.com/paper/2608.17070/) (2026)
- [Can AI Oversight Be Zero Knowledge?](https://mlsanity.com/paper/2610.01995/) (2026)

## Abstract (arXiv)

The black-box service model enables ML service providers to serve clients while keeping their intellectual property and client data confidential. Confidentiality is critical for delivering ML services legally and responsibly, but makes it difficult for outside parties to verify important model properties such as fairness. Existing methods that assess model fairness confidentially lack either (i) reliability because they certify fairness with respect to a static set of data, and therefore fail to guarantee fairness in the presence of distribution shift or service provider malfeasance; and/or (ii) scalability due to the computational overhead of confidentiality-preserving cryptographic primitives. We address these problems by introducing online fairness certificates, which verify that a model is fair with respect to data received by the service provider online during deployment. We then present OATH, a deployably efficient and scalable zero-knowledge proof protocol for confidential online group fairness certification. OATH exploits statistical properties of group fairness via a cut-and-choose style protocol, enabling scalability improvements over baselines.