MITRE ATLAS · AI Model Access
AML.T0044 · 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 and Verify Attack in an offline environment where it is hard to detect their behavior.
Mitigations
- Control Access to AI Models and Data at Rest
- AI Model Distribution Methods
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.