AI RESEARCH
Exposing the Illusion of Fairness: Auditing Vulnerabilities to Distributional Manipulation Attacks
arXiv CS.LG
•
ArXi:2507.20708v2 Announce Type: replace The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing. For binary classifiers, regulatory risk assessment often relies on global fairness metrics such as the Disparate Impact ratio, widely used to evaluate potential discrimination.