Bias in AI Spam Filters: Microsoft Outlook Flagging Legitimate Emails Based on Questionable Keywords

October 22, 2020

AlgorithmWatch study reveals potential racial and content biases in Microsoft Outlook's spam filtering algorithm. Emails mentioning Nigeria or containing financial and sexual health terms are disproportionately flagged as spam, raising concerns about safe and secure AI. This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM). Ready to help prevent such harm? JOIN US
Alleged deployer
yahoo, outlook, laposte, gmx, gmail
Alleged developer
yahoo, microsoft, laposte, google, gmx
Alleged harmed parties
yahoo!-mail-users, microsoft-outlook-users, laposte-users, gmx-users, gmail-users

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/83

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.