Create Proxy AI Model
Description
Adversaries may obtain models to serve as proxies for the target model in use at the victim organization.
Proxy models are used to simulate complete access to the target model in a fully offline manner.
Adversaries may train models from representative datasets, attempt to replicate models from victim inference APIs, or use available pre-trained models.
- ATLAS ID
- AML.T0005
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Predictive AIGenerative AIAgentic AI
Sub-techniques
Mitigations
- AML.M0000Limit Public Release of Information
Limiting release of technical information about a model and training data can reduce an adversary's ability to create an accurate proxy model.
- AML.M0001Limit Model Artifact Release
Limiting the release of model artifacts can reduce an adversary's ability to create an accurate proxy model.
- AML.M0002Predictive AI Output Obfuscation
Obfuscating model outputs can reduce an adversary's ability to produce an accurate proxy model.
- AML.M0004Limit AI Service Query Volume and Rate
Limit inference queries to reduce the labeled outputs available for training a proxy model.
- AML.M0019Control Access to AI Models and Data in Production
Access controls on models APIs can reduce an adversary's ability to produce an accurate proxy model.