Train Proxy via Replication
Sub-technique of AML.T0005 Create Proxy AI Model
Description
Adversaries may replicate a private model.
By repeatedly querying the victim's AI Model Inference API Access, the adversary can collect the target model's inferences into a dataset.
The inferences are used as labels for training a separate model offline that will mimic the behavior and performance of the target model.
A replicated model that closely mimics the target model is a valuable resource in staging the attack.
The adversary can use the replicated model to Craft Adversarial Data for various purposes (e.g. Evade AI Model, Spamming AI System with Chaff Data).
- ATLAS ID
- AML.T0005.001
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Predictive AIGenerative AIAgentic AI
Mitigations
- AML.M0002Predictive AI Output Obfuscation
Obfuscating model outputs restricts an adversary's ability to create an accurate proxy model by querying a model and observing its outputs.
- AML.M0004Limit AI Service Query Volume and Rate
Limit inference queries to reduce the labeled outputs available for training a proxy model.
- AML.M0024AI Telemetry Logging
Telemetry logging can help identify if a proxy training dataset has been exfiltrated.