unawareness

A situation in which sensitive attributes are present, but not included in the training data. Because sensitive attributes are often correlated with other attributes of one's data, a model trained with unawareness about a sensitive attribute could still have disparate impact with respect to that attribute, or violate other fairness constraints.

Practitioners refer to unawareness when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.