Manipulation-Proof Oblivious Audits against Deceptive Model Providers

• URL: http://arxiv.org/abs/2608.04365v1
• Date: Wed, 05 Aug 2026 02:12:54 GMT
• Title: Manipulation-Proof Oblivious Audits against Deceptive Model Providers
• Abstract summary: In regulatory contexts, audits are typically declared or easily detected, enabling model providers to manipulate the process.<n>This vulnerability is particularly acute in the context of fairness evaluations.<n>We introduce a novel audit protocol designed to significantly increase the post-audit detectability of such manipulations.
• Score: 4.614773550999029
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Fairness Auditing: Lower Bounds on Company Manipulation [4.867679624126028]
  Fairness audits are increasingly mandated in high-stakes applications such as hiring, lending, and automated decision-making.<n>Recent work has established fundamental impossibility results for black-box fairness auditing.<n>We quantify the extent of unavoidable post-audit manipulation under finite audit resources.
  arXiv  Detail & Related papers  (2026-08-01T10:11:20Z)
• Sequential Fairness Auditing with Limited Output Access [6.933020649563105]
  External evaluations are becoming increasingly central to the governance of AI systems.<n>In practice, independent auditors often have limited access to deployed models and must rely on query-based interactions.<n>Most existing fairness evaluation methods assume static datasets and fixed-sample statistical tests.<n>We formulate fairness auditing as a tolerance-aware sequential hypothesis-testing problem under limited model output access.
  arXiv  Detail & Related papers  (2026-06-29T14:17:33Z)
• Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? [61.49434544687523]
  We introduce REFLECT, a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments.<n> REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions.<n>Our experiments show that even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures.
  arXiv  Detail & Related papers  (2026-05-18T23:55:08Z)
• IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation [49.796717294455796]
  We present IMMACULATE, a practical auditing framework that detects economically motivated deviations.<n>IMMACULATE selectively audits a small fraction of requests using verifiable computation, achieving strong detection guarantees while amortizing cryptographic overhead.
  arXiv  Detail & Related papers  (2026-02-26T07:21:02Z)
• Governing AI Forgetting: Auditing for Machine Unlearning Compliance [30.173215964349044]
  We introduce the first economic framework for auditing machine unlearning compliance, by integrating certified unlearning theory with regulatory enforcement.<n>We first characterize MU's inherent verification uncertainty using a hypothesis-testing interpretation of certified unlearning.<n>We then propose a game-theoretic model to capture the strategic interactions between the auditor and the operator.
  arXiv  Detail & Related papers  (2026-02-16T08:32:09Z)
• Preventing the Collapse of Peer Review Requires Verification-First AI [49.995126139461085]
  We propose truth-coupling, i.e. how tightly venue scores track latent scientific truth.<n>We formalize two forces that drive a phase transition toward proxy-sovereign evaluation.
  arXiv  Detail & Related papers  (2026-01-23T17:17:32Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• "Show Me You Comply... Without Showing Me Anything": Zero-Knowledge Software Auditing for AI-Enabled Systems [2.2981698355892686]
  This paper introduces ZKMLOps, a novel MLOps verification framework.<n>It operationalizes Zero-Knowledge Proofs (ZKPs)-cryptographic protocols allowing a prover to convince a verifier that a statement is true.<n>We evaluate the framework's practicality through a study of regulatory compliance in financial risk auditing.
  arXiv  Detail & Related papers  (2025-10-30T15:03:32Z)
• Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective [59.61868506896214]
  We show that under standard data coverage assumptions, reinforcement learning is no more statistically difficult than through process supervision.<n>We prove that any policy's advantage function can serve as an optimal process reward model.
  arXiv  Detail & Related papers  (2025-02-14T22:21:56Z)
• The Decisive Power of Indecision: Low-Variance Risk-Limiting Audits and Election Contestation via Marginal Mark Recording [51.82772358241505]
  Risk-limiting audits (RLAs) are techniques for verifying the outcomes of large elections. We define new families of audits that improve efficiency and offer advances in statistical power. New audits are enabled by revisiting the standard notion of a cast-vote record so that it can declare multiple possible mark interpretations.
  arXiv  Detail & Related papers  (2024-02-09T16:23:54Z)
• TrustFed: A Reliable Federated Learning Framework with Malicious-Attack Resistance [8.924352407824566]
  Federated learning (FL) enables collaborative learning among multiple clients while ensuring individual data privacy. In this paper, we propose a hierarchical audit-based FL (HiAudit-FL) framework to enhance the reliability and security of the learning process. Our simulation results demonstrate that HiAudit-FL can effectively identify and handle potential malicious users accurately, with small system overhead.
  arXiv  Detail & Related papers  (2023-12-06T13:56:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.