Efficient Active Auditing of Multi-Group Fairness with Bias Probes

The field of Machine Learning (ML) has increasingly focused on dual objectives: optimizing prediction accuracy while mitigating unfairness bias. Despite efforts in fairness-aware training, improvements over standard Empirical Risk Minimization (ERM) are often limited, making post hoc auditing crucial. Current black-box model auditing methods, which either reconstruct models or directly estimate fairness metrics, offer insufficient insight into the specific data regions contributing to bias. The research focuses on the under-explored area of property-specific auditing, which aims to extract targeted fairness information without requiring full model reconstruction.

The limitations of current fairness-aware ML training and auditing methods present significant challenges to the responsible deployment of artificial intelligence. Effective property-specific auditing is critical for identifying and addressing algorithmic bias at a granular level, thereby enhancing trust and accountability in AI systems, and mitigating potential reputational and regulatory risks.

Machine Learning models are typically trained to balance prediction error minimization with unfairness bias control.

Forward consideration, not a verified fact.