SubTechniqueexecutionATLAS

AML.T0011.000Unsafe AI Artifacts

What it is

Adversaries may develop unsafe AI artifacts that when executed have a deleterious effect. The adversary can use this technique to establish persistent access to systems. These models may be introduced via a [AI Supply Chain Compromise](/techniques/AML.T0010). Serialization of models is a popular technique for model storage, transfer, and loading. However, this format without proper checking presents an opportunity for code execution.

References

  1. https://atlas.mitre.org/techniques/AML.T0011.000

Related by meaning· 6

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

ATLAS
Corrupt AI Model
ATLAS
AI Supply Chain Compromise
ATLAS
Publish Poisoned Models
ATLAS
AI Artifact Collection
ATLAS
Exfiltration via AI Inference API
ATLAS
Discover AI Artifacts
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.