AI System Coverage Map

Scope: ATLAS covers a fundamentally different attack surface than ATT&CK — training pipelines, model weights, inference APIs, prompt injection. Most of it happens inside the AI application or model layer, not the Windows host, so most of this page is an honest map of what this catalog can't see, not a coverage claim.

Version: ATLAS is evolving fast — now at 16 tactics (data version 5.6.0), up from 14 as of this catalog's last check. Two tactics were added since: Lateral Movement (pivoting toward AI Ops infrastructure — model registries, notebooks, training pipelines) and Command and Control (communicating with a compromised AI agent to control it). Also renamed "ML Model Access"/"ML Attack Staging" to AI Model Access/AI Attack Staging — this page uses current terminology.