UTC

AML.T0005

Replicate AI Model Behavior

The result may be a surrogate for attack development, a functional replica, or a student model incorporating selected target capabilities.

  • Tactic Resource Development
  • Tactic AI Attack Adaptation
  • Maturity: Realized
  • Predictive AI
  • Generative AI
  • Agentic AI
Full entry on MITRE ATLAS →
Mitigations
  • Limit Public Release of InformationAML.M0000

    Limit the public release of technical information about the AI stack used in an organization's products or services. Technical knowledge of how AI is used can be leveraged by adversaries to perform targeting and tailor attacks to the target system.

    Policy

  • Limit Model Artifact ReleaseAML.M0001

    Limit public release of technical project details including data, algorithms, model architectures, and model checkpoints that are used in production, or that are representative of those used in production.

    Policy

  • Predictive AI Output ObfuscationAML.M0002

    Reduce the fidelity and amount of information returned by predictive AI inference endpoints to make model discovery, extraction, replication, and black-box adversarial-example optimization more difficult.

    Technical - AI

  • Limit AI Service Query Volume and RateAML.M0004

    Limit the number and rate of requests that users can submit to an AI service. Apply limits by user, API key, tenant, device, or other authenticated identity. Use short-term rate, burst, and concurrency limits together with longer-term usage quotas.

    Technical - Cyber

  • Control Access to AI Models and Data in ProductionAML.M0019

    Require users to verify their identities before accessing a production model. Require authentication for API endpoints and monitor production model queries to ensure compliance with usage policies and to prevent model misuse.

    Policy

  • 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

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