UTC

AML.T0137.003

Training Data Information from AI Models: Extract Memorized Data

Adversaries may elicit and recover sensitive content memorized by a generative AI model during training or fine-tuning. Recovered material may include complete training examples or recognizable portions of text, source code, or images, potentially exposing personal information, private communications, or proprietary material.

  • Tactic Collection
  • Maturity: Demonstrated
  • Predictive AI
  • Generative AI
  • Agentic AI
Full entry on MITRE ATLAS →
Mitigations
  • Validate AI ModelAML.M0008

    Evaluate AI models against defined functional requirements before deployment and throughout their operational lifecycle. Validate newly trained or acquired models and repeat evaluation after fine-tuning, model updates, or changes to the conditions in which the model is used.

    Technical - AI

  • Generative AI GuardrailsAML.M0020

    Guardrails are safety controls placed between users, tools, and generative AI models to evaluate prompts, retrieved context, model outputs, and agent actions before they are accepted, executed, or shown to a user.

    Technical - AI

  • 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.