Techniqueai-model-accessATLAS

AML.T0044Full AI Model Access

What it is

Adversaries may gain full "white-box" access to an AI model. This means the adversary has complete knowledge of the model architecture, its parameters, and class ontology. They may exfiltrate the model to [Craft Adversarial Data](/techniques/AML.T0043) and [Verify Attack](/techniques/AML.T0042) in an offline where it is hard to detect their behavior.

References

  1. https://atlas.mitre.org/techniques/AML.T0044

Related by meaning· 6

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

ATLAS tactic
AI Model Access
ATLAS
AI Model Inference API Access
ATLAS
Exfiltration via AI Inference API
ATLAS
AI-Enabled Product or Service
ATLAS
Corrupt AI Model
ATLAS
Search Open AI Vulnerability Analysis
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.