Fade to Gray: From Black-Box to AI-Antagonistic Audits
Shifting the central focus in AI auditing from assuming truthful model responses to considering the antagonistic interests of an auditor and the AI model being scrutinized.
Authors
- Gilles Trédan (ORCID: https://orcid.org/0000-0003-4473-4332)
- Erwan Le Merrer (ORCID: https://orcid.org/0000-0001-8344-2135)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Laboratoire d'Analyse et d'Architecture des Systèmes (FR)
- Centre Inria de l'Université de Rennes (FR)
- Université de Rennes (FR)
Publication Details
- Journal
- Communications of the ACM
- Published
- 2026-07-22
- DOI
- https://doi.org/10.1145/3780103
- Primary Topic
- Ethics and Social Impacts of AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00