MITRE ATLAS · Collection
AML.T0137 · Training Data Information from AI Models
Adversaries may obtain sensitive information about the data used to train or fine-tune an AI model by analyzing its outputs or behavior. This can expose private associations, personally identifiable information, or proprietary data, creating data privacy concerns and supporting subsequent adversarial operations.
Mitigations
- Adaptive AI Response Degradation
- Privacy-Preserving AI Training and Inference
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.