# Manipulation-Proof Oblivious Audits against Deceptive Model Providers

arXiv: https://arxiv.org/abs/2608.04365 · HTML: https://mlsanity.com/paper/2608.04365/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 52 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [Fairwashing: the risk of rationalization](https://mlsanity.com/paper/1901.09749/) (2019)
- [Fairwashing Explanations with Off-Manifold Detergent](https://mlsanity.com/paper/2007.09969/) (2020)
- [Low Latency Privacy Preserving Inference](https://mlsanity.com/paper/1812.10659/) (2018)
- [Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem](https://mlsanity.com/paper/2310.02521/) (2023)
- [Evaluation Gaps in Machine Learning Practice](https://mlsanity.com/paper/2205.05256/) (2022)
- [The Problem with Metrics is a Fundamental Problem for AI](https://mlsanity.com/paper/2002.08512/) (2020)
- [Algorithmic Auditing and Social Justice: Lessons from the History of Audit Studies](https://mlsanity.com/paper/2109.06974/) (2021)
- [Trustless Audits without Revealing Data or Models](https://mlsanity.com/paper/2404.04500/) (2024)
- [Faking Fairness via Stealthily Biased Sampling](https://mlsanity.com/paper/1901.08291/) (2019)
- [HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter](https://mlsanity.com/paper/2411.15462/) (2024)
- [SoK: Machine Learning Governance](https://mlsanity.com/paper/2109.10870/) (2021)
- [Secure and Confidential Certificates of Online Fairness](https://mlsanity.com/paper/2410.02777/) (2024)
- [Robust ML Auditing using Prior Knowledge](https://mlsanity.com/paper/2505.04796/) (2025)
- [Practical Solutions in Fully Homomorphic Encryption -- A Survey Analyzing Existing Acceleration Methods](https://mlsanity.com/paper/2303.10877/) (2023)
- [PrivFair: a Library for Privacy-Preserving Fairness Auditing](https://mlsanity.com/paper/2202.04058/) (2022)

## Built on by (most cited first, 1 of 1)

- [Robust Decentralized Fairness Auditing](https://mlsanity.com/paper/2610.10199/) (2026)

## Abstract (arXiv)

Audits have emerged as a critical instrument for algorithmic governance, providing a mechanism for external scrutiny and governance of machine learning models. However, ensuring the integrity of such assessments remains a challenging issue. For instance in regulatory contexts, audits are typically declared or easily detected, thus enabling model providers to manipulate the process, whether intentionally or inadvertently. This vulnerability is particularly acute in the context of fairness evaluations, in which providers can often infer sensitive attributes and strategically equalize allocation rates between groups to satisfy fairness metrics. In this paper, we introduce a novel audit protocol designed to significantly increase the post-audit detectability of such manipulations by enabling the auditor to query the model in an oblivious manner. Our approach leverages a Private Information Retrieval mechanism to require the provider to label a large set of instances, while preventing it from knowing which subset will ultimately be used for the audit. The protocol is efficient, imposes minimal overhead on the auditor, and requires no modification to the audited model, its training procedure, or its inference pipeline. We provide theoretical guarantees showing that, under this protocol, a provider attempting to hide unfairness must falsify a significantly larger number of responses, thereby increasing both the difficulty and the likelihood of detection of manipulation. Experimental results across representative audit scenarios confirm the effectiveness and practicality of our approach.