AI 中文总结
该研究将公平性审计建模为公司与审计员的极小极大优化，推导了两种审计机制下审计后人口统计 parity 偏差的下界，实证显示增加审计资源无法消除审计后操纵。
AI 中文摘要
公平性审计在招聘、借贷、自动决策等高风险应用中日益成为强制要求。近期研究已针对黑盒公平性审计确立了基本的不可能性结果，表明足够具表达能力的模型可规避任何审计策略。我们通过量化有限审计资源下不可避免的审计后操纵程度，对这些结果进行补充。我们将公平性审计建模为计算无界的公司与预算受限的审计员之间的极小极大优化问题。我们研究两种审计机制：(i) 使用固定大小审计集来验证公平性的预算受限审计员；(ii) 额外要求审计集在α近似范围内估计已验证模型公平性的预算受限α容忍审计员。针对这两种场景，我们推导了最坏情况下审计后人口统计 parity 偏差的明确下界，该偏差是审计预算、群体不平衡和公平性容忍度的函数。最后，我们使用简单的审计集构造启发式方法，结合线性分类器和神经网络分类器，对这些理论极限进行了实证说明。我们的结果表明，增加审计资源可减少但无法消除审计后操纵的空间，凸显了有限预算公平性验证的基本局限。
英文摘要
Fairness audits are increasingly mandated in high-stakes applications such as hiring, lending, and automated decision-making. Recent work has established fundamental impossibility results for black-box fairness auditing, showing that sufficiently expressive models can evade any auditing strategy. We complement these results by quantifying the extent of unavoidable post-audit manipulation under finite audit resources. We formulate fairness auditing as a min-max optimization between a computationally unbounded company and a budget-constrained auditor. We study two auditing regimes: (i) a budgeted auditor that certifies fairness using a fixed-size audit set, and (ii) a budgeted α-tolerant auditor that additionally requires the audit set to estimate the fairness of the certified model within an α approximation. For both settings, we derive explicit lower bounds on the worst-case post-audit demographic parity deviation as functions of the audit budget, group imbalance, and fairness tolerance. Finally, we empirically illustrate these theoretical limits using simple audit-set construction heuristics with linear and neural network classifiers. Our results demonstrate that increasing audit resources reduces, but does not eliminate, the scope for post-audit manipulation, highlighting fundamental limitations of finite-budget fairness certification.
