APromptRiskDBThreat intelligence atlas
AI Risk

Toxic language

"LM’s may predict hate speech or other language that is “toxic”. While there is no single agreed definition of what constitutes hate speech or toxic speech (Fortuna and Nunes, 2018; Persily and Tucker, 2020; Schmidt and Wiegand, 2017), proposed definitions often include profanities, identity attacks, sleights, insults, threats, sexually explicit content, demeaning language, language that incites violence, or ‘host...

AI Risk1. Discrimination & Toxicity1.2 > Exposure to toxic content2 - Post-deployment

Record summary

A quick snapshot of what this page covers.

Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain1. Discrimination & ToxicityThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

"LM’s may predict hate speech or other language that is “toxic”. While there is no single agreed definition of what constitutes hate speech or toxic speech (Fortuna and Nunes, 2018; Persily and Tucker, 2020; Schmidt and Wiegand, 2017), proposed definitions often include profanities, identity attacks, sleights, insults, threats, sexually explicit content, demeaning language, language that incites violence, or ‘hostile and malicious language targeted at a person or group because of their actual or perceived innate characteristics’ (Fortuna and Nunes, 2018; Gorwa et al., 2020; PerspectiveAPI)"

Domain1. Discrimination & Toxicity
Subdomain1.2 > Exposure to toxic content
Entity2 - AI
Intent2 - Unintentional
Timing2 - Post-deployment
CategoryDiscrimination, Exclusion and Toxicity
SubcategoryToxic language

Suggested mitigations

Defenses that may help with related attacks.

No propagated mitigations. No defense is available through the connected attack methods.

Source

Research source for this risk, when available.