SubTechniqueexfiltrationATLAS

AML.T0024.002Extract AI Model

What it is

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).

References

  1. https://atlas.mitre.org/techniques/AML.T0024.002

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

ATLAS
Exfiltration via AI Inference API
ATLAS tactic
AI Model Access
ATLAS
AI Model Inference API Access
ATLAS
Exfiltration via Cyber Means
ATLAS
Full AI Model Access
ATLAS
Acquire Public AI Artifacts
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.