Full AI Model Access
Description
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.
- ATLAS ID
- AML.T0044
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Predictive AIGenerative AIAgentic AI
Mitigations
- AML.M0005Control Access to AI Models and Data at Rest
Access controls on models and data at rest can help prevent full model access.
- AML.M0017AI Model Distribution Methods
Not distributing the model in software to edge devices, can limit an adversary's ability to gain full access to the model.