MIT AI Risk Repository · Risk Category · 62.08.00
Direct Harm Domains (content safety harms)
Description
"For “content safety harms,” the output of the model is directly harmful, as a result of the content itself being harmful or dangerous to individuals or groups."
From Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Subdomain
- 1.2 Exposure to toxic content
- Causal entity
- Not coded
- Intent
- Not coded
- Timing
- Not coded
Subdomain definition: AI exposing users to harmful, abusive, unsafe or inappropriate content. May involve AI creating, describing, providing advice, or encouraging action. Examples of toxic content include hate-speech, violence, extremism, illegal acts, child sexual abuse material, as well as content that violates community norms such as profanity, inflammatory political speech, or pornography.
Real-world incidents in this subdomain
- KBS AI Translation Subtitles Reportedly Broadcast Profanity During Artemis II Launch Livestream
- Grok Allegedly Generated Publicly Visible Sexist Abuse Targeting Swiss Finance Minister Karin Keller-Sutter After X User Prompt
- Trump Reportedly Posted Purportedly AI-Generated Racist Video Depicting Barack and Michelle Obama as Apes on Truth Social
- Tencent's WeChat-Integrated Yuanbao Chatbot Reportedly Insulted User During Coding Debug Request
- Alleged Harmful Outputs and Data Exposure in Children's AI Products by FoloToy, Miko, and Character.AI
- AI Training Dataset for Detecting Nudity Allegedly Found to Contain CSAM Images of Identified Victims