AML.T0018
Manipulate AI Model
Description
Adversaries may manipulate an AI model artifact or its bundled components to change AI system behavior, introduce malicious code, or establish persistent malicious functionality. This may include modifying model weights, model architecture, or prompt-construction logic. Manipulated artifacts may retain expected behavior under ordinary conditions while activating malicious behavior only for selected inputs, contexts, or deployment conditions.
Honesty-tier rationale
Persistence needs durable tampering with real model weights or infrastructure; the mechanism can be shown, but real persistence cannot be faked in a browser.
Sub-techniques
- AML.T0018.000 — Poison AI Model
- AML.T0018.001 — Modify AI Model Architecture
- AML.T0018.002 — Embed Malware
- AML.T0018.003 — Modify Prompt Construction Logic