H3XAOperational intelligence
Live analytical pictureEvidence before assessment
Threat intelligence / Technique

Full AI Model Access

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 environment where it is hard to detect their behavior.

Technique
TypeTechnique
External ID—
First seen2026-08-14
Last seen2026-08-14

Confidence

—

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 environment where it is hard to detect their behavior.

6 recorded

Relationships

mitigates
from AI Model Distribution Methods
Mitigation
mitigates
from Control Access to AI Models and Data at Rest
Mitigation
uses
from AI Model Tampering via Supply Chain Attack
Campaign
uses
from Backdoor Attack on Deep Learning Models in Mobile Apps
Campaign
uses
from Google Photos AI Model Extraction
Campaign
uses
from Organization Confusion on Hugging Face
Campaign
1 external

References

mitre-atlas
AML.T0044
open
Continue into the dataIntelligence explorerHow to read the graphEvidence & provenance