PromptRiskDBThreat intelligence atlas
AI Risk

Model diversion

"Model Diversion takes model manipulation one step further, by repurposing (often open-source) generative AI models in a way that diverts them from their intended functionality or from the use cases envisioned by their developers (Lin et al., 2024). An example of this is training the BERT open source model on the DarkWeb to create DarkBert.7"

View related techniquesRead profile
AI Risk4. Malicious Actors & Misuse4.2 > Cyberattacks, weapon development or use, and mass harm2 - Post-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
Timing2 - Post-deployment
CategoryMisuse tactics to compromise GenAI systems (Model integrity)
SubcategoryModel diversion

Related techniques

Attack methods connected to this risk.

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.