MITRE ATLASsub-technique
AML.T0024.002 Extract AI Model
- Tactics
- Exfiltration
- Created
- 2021-05-13
Description
Adversaries may extract a functional copy of 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.
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.
Related
Subtechnique of · MITRE ATLAS (1)
- AML.T0024 Exfiltration via AI Inference API technique
Tactic · MITRE ATLAS (1)
- AML.TA0010 Exfiltration tactic