PromptRiskDBThreat intelligence atlas
AI Risk

Acquisition of a goal to harm society

"cases of AI systems being given the outright goal of harming humanity (ChaosGPT);"

AI Risk4. Malicious Actors & Misuse4.2 > Cyberattacks, weapon development or use, and mass harm1 - Pre-deployment

Record summary

A quick snapshot of what this page covers.

Techniques1Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain4. Malicious Actors & MisuseThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

Domain4. Malicious Actors & Misuse
Subdomain4.2 > Cyberattacks, weapon development or use, and mass harm
Entity1 - Human
Intent1 - Intentional
Timing1 - Pre-deployment
CategoryDangerous capabilities in AI systems
SubcategoryAcquisition of a goal to harm society

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.