Stable Diffusion Reportedly Exhibited Biases for Prompts Featuring Professions

August 22, 2022

Stable Diffusion reportedly posed risks of bias and stereotyping along gender and cultural lines for prompts containing descriptors and professions. This raises concerns about the potential harm that can be caused by biased AI models, particularly in industries where representation matters. For more information on Project Cerebellum's work in responsible AI and harm prevention, go to JOIN US.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Stability AI
Alleged developer
Stability AI, Runway, LAION, EleutherAI, CompVis LMU
Alleged harmed parties
Women and girls, Women, Minority groups

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/529

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.