Threat intelligence / Technique

Extract AI Model

Adversaries may extract a functional copy of a private model. By repeatedly querying the victim's [AI Model Inference API Access](/techniques/AML.T0040), 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. Adversaries may extract the model to avoid paying per query in an artificial-intelligence-as-a-service (AIaaS) setting. Model extraction is used for [AI Intellectual Property Theft](/techniques/AML.T0048.004).

Technique

TypeTechnique

External ID—

First seen2026-08-14

Last seen2026-08-14

Confidence

—

Adversaries may extract a functional copy of a private model. By repeatedly querying the victim's [AI Model Inference API Access](/techniques/AML.T0040), 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. Adversaries may extract the model to avoid paying per query in an artificial-intelligence-as-a-service (AIaaS) setting. Model extraction is used for [AI Intellectual Property Theft](/techniques/AML.T0048.004).

6 recorded

Relationships

mitigates

from AI Red Team

Mitigation

mitigates

from AI Telemetry Logging

Mitigation

mitigates

from Limit AI Service Query Volume and Rate

Mitigation

mitigates

from Predictive AI Output Obfuscation

Mitigation

subtechnique-of

to Exfiltration via AI Inference API

Technique

uses

from Model Distillation Campaigns Targeting Anthropic Claude

Campaign

1 external

References

mitre-atlas

AML.T0024.002