Black-Box Audits for Group Distribution Shifts. (arXiv:2209.03620v1 [cs.LG])

When a model informs decisions about people, distribution shifts can create
undue disparities. However, it is hard for external entities to check for
distribution shift, as the model and its training set are often proprietary. In
this paper, we introduce and study a black-box auditing method to detect cases
of distribution shift that lead to a performance disparity of the model across
demographic groups. By extending techniques used in membership and property
inference attacks -- which are designed to expose …

audits box distribution shifts