Record summary
A quick snapshot of what this page covers.
Risk profile
How this risk is described and categorized.
"The model can break out of its local environment (e.g. using a vulnerability in its underlying system or suborning an engineer). The model can exploit limitations in the systems for monitoring its behaviour post-deployment. The model could independently generate revenue (e.g. by offering crowdwork services, ransomware attacks), use these revenues to acquire cloud computing resources, and operate a large number of other AI systems. The model can generate creative strategies for uncovering information about itself or exfiltrating its code and weights."
Suggested mitigations
Defenses that may help with related attacks.
Source
Research source for this risk, when available.
Included resource
Model Evaluation for Extreme Risks
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.
