Protected Attributes
Explore the definition and importance of protected attributes in AI fairness. Learn to identify sensitive features and proxy attributes that may cause bias. Understand key legal concepts such as disparate treatment and disparate impact, and how they affect fairness measurement. This lesson equips you to recognize potential bias sources and evaluate their impact on AI decision-making in different contexts.
We'll cover the following...
Sensitive attributes
Before measuring potential biases, we must consider what attributes can be a subject of discrimination. Some of them can be defined by law (when there is a related regulation, e.g., credit scoring). We call them protected or sensitive attributes and define them as attributes we don’t want to discriminate against. But, of course, the decision if a specific attribute is sensitive may depend on the particular context. That’s why a good understanding of the problem is crucial.
Protected attributes can be included in the data directly; features like age, gender, and marital status should grab our attention. We should proceed with them carefully as a potential source of model bias. However, even if such an attribute is not visible for the model, it still can have an unwanted impact. Let’s consider the zip code. Assuming it is not a protected attribute by itself, it can be heavily correlated with ...