发表机构
Toronto Metropolitan University; St. Clair College（多伦多城市大学; 圣克莱尔学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对部署后漂移导致的无声故障，提出FMMO框架，结合全局替代模型与利用率测量，检测局部归因稳定与全局漂移的分歧，以发现标准局部XAI忽视的公平性恶化。
AI 中文摘要
部署后的漂移对算法问责制构成严重风险，尤其是在真实标签延迟且性能退化成为“无声故障”的情况下。虽然可解释人工智能（XAI）常被依赖用于审计这些变化，但我们证明，流行的局部归因方法（如TreeSHAP）即使在模型可靠性崩溃时也可能表现出误导性的稳定性。在本文中，我们提出了一个模型监控与可观测性框架（FMMO），旨在揭示局部解释稳定性与全局分布漂移之间的分歧。利用基准数据集、合成数据集和真实世界数据集，我们表明局部XAI方法无法标记漂移引起的差异性影响，特别是在受保护群体的假阳性率飙升而特征归因保持不变的情况下。通过将全局替代模型与模型利用率测量相结合，FMMO缓解了这一公平性盲点，确保利益相关者能够检测到标准局部XAI工具忽视的歧视性恶化。
英文摘要
Post-deployment drift poses a critical risk to algorithmic accountability, particularly when ground truth labels are delayed and performance degradation becomes a "silent failure". While Explainable AI (XAI) is often relied upon to audit these shifts, we demonstrate that popular local attribution methods (e.g., TreeSHAP) can exhibit misleading stability even as model reliability collapses. In this paper, we propose a Framework for Model Monitoring and Observability (FMMO) designed to expose the divergence between local explanation stability and global distribution shifts. Using benchmark, synthetic, and real-world datasets, we show that local XAI methods fail to flag drift-induced disparate impact, specifically where False Positive Rates spike for protected groups while feature attributions remain unchanged. By integrating global surrogate models with model utilization measurements, FMMO mitigates this fairness blind spot, ensuring that stakeholders can detect discriminatory deterioration that standard local XAI tools overlook.
