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.
"The model can discover vulnerabilities in systems (hardware, software, data). It can write code for exploiting those vulnerabilities. It can make effective decisions once it has gained access to a system or network, and skilfully evade threat detection and response (both human and system) whilst focusing on a specific objective. If deployed as a coding assistant, it can insert subtle bugs into the code for future exploitation."
Domain4. Malicious Actors & Misuse
Subdomain4.2 > Cyberattacks, weapon development or use, and mass harm
Entity2 - AI
Intent1 - Intentional
Timing2 - Post-deployment
CategoryCyber-offense
Subcategoryn/a
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
Model Evaluation for Extreme Risks
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.