Racial, Gender, and Intersectional Bias in Unsupervised Image Generation Models: iGPT and SimCLR

June 17, 2020

Uncovering racial, gender, and intersectional biases in popular unsupervised image generation models such as iGPT and SimCLR. These models, trained using Internet data, inadvertently produced stereotypical depictions. This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM). JOIN US: Contribute to harm prevention by implementing guardrails for AI.
Alleged deployer
openai, google
Alleged developer
openai, google
Alleged harmed parties
gender-minority-groups, racial-minority-groups, underrepresented-groups-in-training-data

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/367

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.