Record summary
A quick snapshot of what this page covers.
Risk profile
How this risk is described and categorized.
"The advanced capabilities and widespread availability of generative AI models make it possible for malicious actors to conduct harmful activities with great efficiency and on a large scale, simultaneously reducing their operational costs. Cybercriminals can “jailbreak” AI tools to generate sensitive and harmful content. They can also exploit generative AI models to create content that is persuasive and tailored to a targeted individual."
Suggested mitigations
Defenses that may help with related attacks.
Use Multi-Modal Sensors
Deepfake Detection
User Training
Source
Research source for this risk, when available.
Included resource
Regulating under Uncertainty: Governance Options for Generative AI
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.
