AltaySec · ATLAS 2026.07
AML.T0018

Manipulate AI Model

C · Explainer (cannot be honestly simulated in-browser) AML.TA0006 · Persistence AML.TA0001 · AI Attack Staging

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

Source

← Back to the matrix