# P2NIA: Privacy-Preserving Non-Iterative Auditing

arXiv: https://arxiv.org/abs/2504.00874 · HTML: https://mlsanity.com/paper/2504.00874/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 26 of 26)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response](https://mlsanity.com/paper/1407.6981/) (2014)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [Winning the NIST Contest: A scalable and general approach to differentially private synthetic data](https://mlsanity.com/paper/2108.04978/) (2021)
- [AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data](https://mlsanity.com/paper/2201.12677/) (2022)
- [Benchmarking Differentially Private Synthetic Data Generation Algorithms](https://mlsanity.com/paper/2112.09238/) (2021)
- [Graphical-model based estimation and inference for differential privacy](https://mlsanity.com/paper/1901.09136/) (2019)
- [AI auditing: The Broken Bus on the Road to AI Accountability](https://mlsanity.com/paper/2401.14462/) (2024)
- [Blind Justice: Fairness with Encrypted Sensitive Attributes](https://mlsanity.com/paper/1806.03281/) (2018)
- [Local, Private, Efficient Protocols for Succinct Histograms](https://mlsanity.com/paper/1504.04686/) (2015)
- [A survey of bias in Machine Learning through the prism of Statistical Parity for the Adult Data Set](https://mlsanity.com/paper/2003.14263/) (2020)
- [Optimal Schemes for Discrete Distribution Estimation under Locally Differential Privacy](https://mlsanity.com/paper/1702.00610/) (2017)
- [A Statistical Test for Probabilistic Fairness](https://mlsanity.com/paper/2012.04800/) (2020)
- [Faking Fairness via Stealthily Biased Sampling](https://mlsanity.com/paper/1901.08291/) (2019)
- [Certifying Some Distributional Fairness with Subpopulation Decomposition](https://mlsanity.com/paper/2205.15494/) (2022)
- [Facebook Ads Monitor: An Independent Auditing System for Political Ads on Facebook](https://mlsanity.com/paper/2001.10581/) (2020)
- [Algorithmic audits of algorithms, and the law](https://mlsanity.com/paper/2203.03711/) (2022)
- [Verifiable Fairness: Privacy-preserving Computation of Fairness for Machine Learning Systems](https://mlsanity.com/paper/2309.06061/) (2023)
- [A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results](https://mlsanity.com/paper/2405.14725/) (2024)
- [PrivFair: a Library for Privacy-Preserving Fairness Auditing](https://mlsanity.com/paper/2202.04058/) (2022)
- [Privacy Amplification via Shuffling: Unified, Simplified, and Tightened](https://mlsanity.com/paper/2304.05007/) (2023)
- [Multi-Dimensional Randomized Response](https://mlsanity.com/paper/2010.10881/) (2020)
- [Fairness Auditing with Multi-Agent Collaboration](https://mlsanity.com/paper/2402.08522/) (2024)

## Built on by (most cited first, 2 of 2)

- [Threat Modeling for Enhancing Security of IoT Audio Classification Devices under a Secure Protocols Framework](https://mlsanity.com/paper/2509.14657/) (2025)
- [Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification](https://mlsanity.com/paper/2607.21839/) (2026)

## Abstract (arXiv)

The emergence of AI legislation has increased the need to assess the ethical compliance of high-risk AI systems. Traditional auditing methods rely on platforms' application programming interfaces (APIs), where responses to queries are examined through the lens of fairness requirements. However, such approaches put a significant burden on platforms, as they are forced to maintain APIs while ensuring privacy, facing the possibility of data leaks. This lack of proper collaboration between the two parties, in turn, causes a significant challenge to the auditor, who is subject to estimation bias as they are unaware of the data distribution of the platform. To address these two issues, we present P2NIA, a novel auditing scheme that proposes a mutually beneficial collaboration for both the auditor and the platform. Extensive experiments demonstrate P2NIA's effectiveness in addressing both issues. In summary, our work introduces a privacy-preserving and non-iterative audit scheme that enhances fairness assessments using synthetic or local data, avoiding the challenges associated with traditional API-based audits.