APromptRiskDBThreat intelligence atlas
AI Risk

Direct Harm Domains (content safety harms)

"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."

AI Risk1. Discrimination & Toxicity1.2 > Exposure to toxic content4 - Not coded

Record summary

A quick snapshot of what this page covers.

Techniques2Attack methods connected to this risk.
Mitigations2Defenses that may help with related attacks.
Domain1. Discrimination & ToxicityThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

Domain1. Discrimination & Toxicity
Subdomain1.2 > Exposure to toxic content
Entity4 - Not coded
Intent4 - Not coded
Timing4 - Not coded
CategoryDirect Harm Domains (content safety harms)
Subcategoryn/a

Suggested mitigations

Defenses that may help with related attacks.

AI Telemetry Logging

DeploymentMonitoring and Maintenance
LifecycleDeployment + 1 moreCategoryTechnical - Cyber

Source

Research source for this risk, when available.