MITRE ATLASsub-technique

AML.T0005.000 Train Proxy via Gathered AI Artifacts

Published 2021-05-13 Modified 2025-04-09 Official page ↗
Tactics
Ai Attack Staging
Created
2021-05-13

Description

Proxy models may be trained from AI artifacts (such as data, model architectures, and pre-trained models) that are representative of the target model gathered by the adversary. This can be used to develop attacks that require higher levels of access than the adversary has available or as a means to validate pre-existing attacks without interacting with the target model.

Related

Subtechnique of · MITRE ATLAS (1)

Tactic · MITRE ATLAS (1)

Referenced by MITRE ATLAS · mitigates (2)

  • AML.M0000 Limit Public Release of Information mitigation
  • AML.M0001 Limit Model Artifact Release mitigation