SSG coverage claim · MITRE ATLAS-mapped

Browse AI-system risk by MITRE ATLAS

Browse the MITRE ATLAS v2026.08 tactic & technique taxonomy for AI systems, alongside SSG's own derived coverage tier for each technique — see the methodology note below for exactly what that tier does and does not claim.

AML.T0011.000 Partial Sub-technique of AML.T0011

Unsafe AI Artifacts

Adversaries may develop new AI artifacts or manipulate existing AI artifacts that have a deleterious effect when loaded, executed, interpreted, or used for inference by a victim.

Tactics

Execution

ATT&CK cross-reference

No Enterprise ATT&CK cross-reference.

ATLAS mitigations & SSG coverage

AML.M0011 Restrict Library Loading Partial Install-guard ASK on dependency additions

AML.M0013 Code Signing Partial Published rulesets are signed and transparency-logged; does not sign models

AML.M0014 Verify AI Artifacts Not addressed AI artifact verification pipeline

AML.M0016 Vulnerability Scanning Partial Dependency audit runs in the release gate

AML.M0018 User Training Not addressed Human training program

AML.M0023 AI Bill of Materials Partial SBOM ships with the product; not a model bill of materials

Methodology. Catalog: MITRE ATLAS v2026.08 (atlas.mitre.org). Coverage tiers are derived from MITRE's own published mitigation↔technique mappings — never hand-assigned per technique. SSG's claim is limited to which ATLAS mitigations it implements as controls; it does not claim to cover ATLAS techniques directly. A tier records which SSG control exists for a MITRE-published mitigation — it is not a statement about outcome, and it is not a certification, an audit result, or an endorsement by MITRE.