SubTechniqueai-attack-stagingATLAS

AML.T0005.000Train Proxy via Gathered AI Artifacts

What it is

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.

References

  1. https://atlas.mitre.org/techniques/AML.T0005.000

Related by meaning· 6

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

ATLAS
Create Proxy AI Model
ATLAS tactic
AI Attack Staging
ATLAS
Acquire Public AI Artifacts
ATLAS
AI Artifact Collection
ATLAS
Discover AI Artifacts
ATLAS
Craft Adversarial Data
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.