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.
In Black-Box attacks, the adversary has black-box (i.e. [AI Model Inference API Access](/techniques/AML.T0040) via API access) access to the target model.
Tactics
AI Attack Adaptation
ATT&CK cross-reference
No Enterprise ATT&CK cross-reference.
ATLAS mitigations & SSG coverage
AML.M0002
Predictive AI Output Obfuscation
Not addressed
Model-side output transform
AML.M0003
Predictive AI Model Hardening
Not addressed
Training-time model hardening
AML.M0004
Limit AI Service Query Volume and Rate
Partial
Usage metering per device; not a general-purpose rate limiter
AML.M0006
Predictive AI Ensembles
Not addressed
Model architecture choice
AML.M0010
Predictive AI Input Restoration
Not addressed
Model-side input reconstruction
AML.M0015
Predictive AI Adversarial Input Detection
Not addressed
Model-side adversarial input detection
AML.M0019
Control Access to AI Models and Data in Production
Partial
Fail-closed entitlement gating on production value surfaces
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.