Stable Diffusion Exhibited Biases for Prompts Featuring Professions

August 22, 2022

AI model Stable Diffusion reportedly exhibited biases in responses to prompts related to professions, raising concerns about gender and cultural stereotyping. Embracing responsible AI principles and trustworthy AI practices can help prevent such incidents. For those interested in shaping the future of safe and secure AI practices, JOIN US. This incident highlights the need for governance and mapping within HISPI Project Cerebellum TAIM.

Matched TAIM controls

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

MEASURE 2.6 — similarity 0.706, rank 1. TAIM detail and related incidents →
MEASURE 4.3 — similarity 0.699, rank 2. TAIM detail and related incidents →
MAP 1.6 — similarity 0.693, rank 3. TAIM detail and related incidents →

Alleged deployer: stability-ai
Alleged developer: stability-ai, runway, laion, eleutherai, compvis-lmu
Alleged harmed parties: racial-minority-groups, women, gender-minority-groups

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.