{
  "id": 16670,
  "url": "https://arxiv.org/abs/2608.04365v1",
  "title": "Manipulation-Proof Oblivious Audits against Deceptive Model Providers",
  "summary": "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 evaluat",
  "authors": "Augustin Godinot, Sofiane Azogagh, Julien Ferry, Sébastien Gambs",
  "category": "research",
  "topics": "bias-fairness,regulation,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-05T02:12:54.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/16670",
  "original_url": "https://arxiv.org/abs/2608.04365v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}