UTC

AML.T0137.001

Training Data Information from AI Models: Infer Properties

Adversaries may infer sensitive global properties of the data used to train an AI model. Properties may include dataset provenance, population composition, relative class proportions, domain coverage, collection period, or the presence of a category or group.

  • Tactic Collection
  • Maturity: Feasible
  • Predictive AI
  • Generative AI
  • Agentic AI
Full entry on MITRE ATLAS →
Mitigations
  • Adaptive AI Response DegradationAML.M0040

    Reduce the utility of AI model outputs for unauthorized model replication, knowledge distillation, or inference about training data by dynamically modifying responses when suspected extraction activity or privacy attacks are detected.

    Technical - AI

  • Privacy-Preserving AI Training and InferenceAML.M0041

    Use privacy-preserving mechanisms throughout model training and inference to limit disclosure of sensitive training or inference data. These mechanisms can reduce the risk that model outputs reveal sensitive information, such as individual training records, and can also protect sensitive training data from exposure to model developers or operators.

    Technical - AI

From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.