AI engineering glossary · AI ethics law product
What is fairness through unawareness?
Fairness through unawareness (also called blindness to protected attributes): The simple approach of dropping protected attributes such as gender or caste from a model's inputs in the hope of making it fair. It often fails because other features act as proxies for the removed ones, and without the attribute you cannot even measure group differences.
Fairness through unawareness: an example
A team deletes the gender column from a hiring model, but the model still rates women lower using hobbies and career gaps that correlate with gender.
Related terms
More AI ethics law product terms
- Fallback behavior
- Federated learning
- Four-fifths rule
- GDPR
- General-purpose AI model
- Global explanation
- High-risk AI system
- Historical bias
Where you learn it
Fairness through unawareness is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.