MITRE ATLAS · Discovery, Collection
AML.T0144 · Recover AI Model Internals
Adversaries may infer or recover non-public AI model internals through analysis of model behavior or exposed information. Targets may include architecture, layer dimensions, hyperparameters, decision-tree structure, projection matrices, or numerical parameters.
Mitigations
- Adaptive AI Response Degradation
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.