Record summary
A quick snapshot of what this page covers.
Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domainn/aThe broad risk area this belongs to.
Risk profile
How this risk is described and categorized.
Domainn/a
SubdomainX.1 > Excluded
Entity3 - Other
Intent2 - Unintentional
Timing3 - Other
CategoryUser Intent
SubcategoryUnintended Consequences
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.
Included resource
Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.