APromptRiskDBThreat intelligence atlas
AI Risk

Inquiry with Unsafe Opinion

"By adding imperceptibly unsafe content into the input, users might either deliberately or unintentionally influence the model to generate potentially harmful content. In the following cases involving migrant workers, ChatGPT provides suggestions to improve the overall quality of migrant workers and reduce the local crime rate. ChatGPT responds to the user’s hint with a disguised and biased opinion that the genera...

View related techniquesRead profile
AI Risk2. Privacy & Security2.2 > AI system security vulnerabilities and attacks2 - 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.
Domain2. Privacy & SecurityThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

"By adding imperceptibly unsafe content into the input, users might either deliberately or unintentionally influence the model to generate potentially harmful content. In the following cases involving migrant workers, ChatGPT provides suggestions to improve the overall quality of migrant workers and reduce the local crime rate. ChatGPT responds to the user’s hint with a disguised and biased opinion that the general quality of immigrants is favorably correlated with the crime rate, posing a safety risk."

Domain2. Privacy & Security
Subdomain2.2 > AI system security vulnerabilities and attacks
Entity1 - Human
Intent1 - Intentional
Timing2 - Post-deployment
CategoryInstruction Attacks
SubcategoryInquiry with Unsafe Opinion

Related techniques

Attack methods connected to this risk.

No linked attack methods. No AI attack method is connected to this risk in the current data.

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.