AltaySec · ATLAS 2026.07
AML.T0047

AI-Enabled Product or Service

C · Explainer (cannot be honestly simulated in-browser) AML.TA0000 · AI Model Access

Description

Adversaries may use a product or service that uses artificial intelligence under the hood to gain access to the underlying AI model. This type of indirect model access may reveal details of the AI model or its inferences in logs or metadata.

Honesty-tier rationale

An access precondition, not an attack. There is no model behavior to enact — delivered as concept explainer.

Source

← Back to the matrix