Paper2018
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification
Joy Buolamwini & Timnit Gebru
Auditing commercial face classifiers by skin tone and gender together, rather than one at a time, exposes error rates an order of magnitude worse for darker-skinned women.
- Level
- Intermediate
- Access
- Free
- Length
- —
- Copy
- link checked 17 Sept 2026
- Filed under
- AI Ethics, Policy & Society