PromptRiskDBThreat intelligence atlas
AI Risk

Contextual Hazards

"Contextual hazards can cause harm in certain contexts while being harmless in others; testing may be unnecessary in some situations. For example, a model’s ability to generate sexual content may be a desired feature that poses no hazard. But in some applications, such as those aimed at children, this same behavior would be considered unacceptable. In cases where a particular contextual hazard is relevant to the a...

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

Record summary

A quick snapshot of what this page covers.

Techniques1Attack 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.

"Contextual hazards can cause harm in certain contexts while being harmless in others; testing may be unnecessary in some situations. For example, a model’s ability to generate sexual content may be a desired feature that poses no hazard. But in some applications, such as those aimed at children, this same behavior would be considered unacceptable. In cases where a particular contextual hazard is relevant to the application, assessment-standard implementers could exclude that category. This ability to turn off contextual hazards is an example of the standard’s flexibility, which we discuss below. Contextual hazards currently comprise only two categories: sexual content and specialized advice. Future versions will likely expand this group."

Domain1. Discrimination & Toxicity
Subdomain1.2 > Exposure to toxic content
Entity2 - AI
Intent3 - Other
Timing2 - Post-deployment
CategoryContextual Hazards
Subcategoryn/a

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.