PromptRiskDBThreat intelligence atlas

Mental Health

AI Risk

"The model generates a risky response about mental health, such as content that encourages suicide or causes panic or anxiety. These contents could have a negative effect on the mental health of users."

Overview

A source-backed snapshot of this AI risk.

Techniques1Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Records2Source records unified into this concept.

Risk profile

How the MIT AI Risk Repository categorizes this risk.

Domain3. Misinformation
Subdomain3.1 > False or misleading information; X.1 > Excluded
Entity2 - AI; 4 - Not coded
Intent3 - Other; 4 - Not coded
Timing2 - Post-deployment; 4 - Not coded
CategoryTypical safety scenarios; Not-Suitable-for-Work (NSFW) Prompts
SubcategoryMental Health

Merged risk records

Source records unified into this canonical risk concept.

2 recordsView all →

MITRISK-Sun2023-27.01.06 - Mental Health

"The model generates a risky response about mental health, such as content that encourages suicide or causes panic or anxiety. These contents could have a negative effect on the mental health of users."

Domain3. MisinformationSubdomain3.1 > False or misleading informationSourceSafety Assessment of Chinese Large Language ModelsYear2023

MITRISK-Cui2024-02.11.05 - Mental Health

N/A

SubdomainX.1 > ExcludedSourceRisk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model SystemsYear2024

Related techniques

Attack methods connected to this risk.

1 recordView all related techniques →

Mitigations

Defenses that may help with related attacks.

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

Source evidence

Research source for this risk, when available.

View all sources →