AudiFair: Privacy-Preserving Framework for Auditing Fairness

Elisaweta Masserova, Kshitij Kulkarni, Antigoni Polychroniadou, Ron D. Rothblum, Akira Takahashi
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:4353-4380, 2026.

Abstract

Ensuring fairness in {AI} is challenging, especially when privacy concerns prevent access to proprietary models and training data. We propose a cryptographic framework for auditing fairness without requiring model disclosure. Unlike existing solutions – which either fail to capture attack vectors enabling dishonest model providers to pass audits unfairly, or require continuous auditing during deployment involving real-world users – our framework is the first to simultaneously achieve the following: $\textbf{(1) Model Privacy}$: Proprietary model details remain hidden from verifiers; $\textbf{(2)}$ A dishonest model provider cannot cause a non-compliant model to pass the fairness audit without detection by the verifier; $\textbf{(3) Pre-deployment Certification}$: The certification can be conducted entirely prior to deployment, without requiring interaction with or data from real-world users; $\textbf{(4) Test Data Transparency}$: Test data for auditing is generated in a transparent and accountable way, preventing dishonest parties from manipulating it. We achieve these goals by carefully combining cryptographic commitments, coin tossing, and zero-knowledge proofs. We evaluate our protocol on decision trees, XGBoost, and neural networks. Our results confirm the practicality of our approach: for a dataset with 10,000 samples and 10 features, and an XGBoost model with 100 trees of depth 3, proof generation takes 42 seconds and verification takes 2 seconds.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-masserova26a, title = {AudiFair: Privacy-Preserving Framework for Auditing Fairness}, author = {Masserova, Elisaweta and Kulkarni, Kshitij and Polychroniadou, Antigoni and Rothblum, Ron D. and Takahashi, Akira}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {4353--4380}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/masserova26a/masserova26a.pdf}, url = {https://proceedings.mlr.press/v337/masserova26a.html}, abstract = {Ensuring fairness in {AI} is challenging, especially when privacy concerns prevent access to proprietary models and training data. We propose a cryptographic framework for auditing fairness without requiring model disclosure. Unlike existing solutions – which either fail to capture attack vectors enabling dishonest model providers to pass audits unfairly, or require continuous auditing during deployment involving real-world users – our framework is the first to simultaneously achieve the following: $\textbf{(1) Model Privacy}$: Proprietary model details remain hidden from verifiers; $\textbf{(2)}$ A dishonest model provider cannot cause a non-compliant model to pass the fairness audit without detection by the verifier; $\textbf{(3) Pre-deployment Certification}$: The certification can be conducted entirely prior to deployment, without requiring interaction with or data from real-world users; $\textbf{(4) Test Data Transparency}$: Test data for auditing is generated in a transparent and accountable way, preventing dishonest parties from manipulating it. We achieve these goals by carefully combining cryptographic commitments, coin tossing, and zero-knowledge proofs. We evaluate our protocol on decision trees, XGBoost, and neural networks. Our results confirm the practicality of our approach: for a dataset with 10,000 samples and 10 features, and an XGBoost model with 100 trees of depth 3, proof generation takes 42 seconds and verification takes 2 seconds.} }
Endnote
%0 Conference Paper %T AudiFair: Privacy-Preserving Framework for Auditing Fairness %A Elisaweta Masserova %A Kshitij Kulkarni %A Antigoni Polychroniadou %A Ron D. Rothblum %A Akira Takahashi %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-masserova26a %I PMLR %P 4353--4380 %U https://proceedings.mlr.press/v337/masserova26a.html %V 337 %X Ensuring fairness in {AI} is challenging, especially when privacy concerns prevent access to proprietary models and training data. We propose a cryptographic framework for auditing fairness without requiring model disclosure. Unlike existing solutions – which either fail to capture attack vectors enabling dishonest model providers to pass audits unfairly, or require continuous auditing during deployment involving real-world users – our framework is the first to simultaneously achieve the following: $\textbf{(1) Model Privacy}$: Proprietary model details remain hidden from verifiers; $\textbf{(2)}$ A dishonest model provider cannot cause a non-compliant model to pass the fairness audit without detection by the verifier; $\textbf{(3) Pre-deployment Certification}$: The certification can be conducted entirely prior to deployment, without requiring interaction with or data from real-world users; $\textbf{(4) Test Data Transparency}$: Test data for auditing is generated in a transparent and accountable way, preventing dishonest parties from manipulating it. We achieve these goals by carefully combining cryptographic commitments, coin tossing, and zero-knowledge proofs. We evaluate our protocol on decision trees, XGBoost, and neural networks. Our results confirm the practicality of our approach: for a dataset with 10,000 samples and 10 features, and an XGBoost model with 100 trees of depth 3, proof generation takes 42 seconds and verification takes 2 seconds.
APA
Masserova, E., Kulkarni, K., Polychroniadou, A., Rothblum, R.D. & Takahashi, A.. (2026). AudiFair: Privacy-Preserving Framework for Auditing Fairness. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:4353-4380 Available from https://proceedings.mlr.press/v337/masserova26a.html.

Related Material