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.
Adversaries can [Craft Adversarial Data](/techniques/AML.T0043) that prevents an AI model from correctly identifying the contents of the data or [Generate Deepfakes](/techniques/AML.T0088) that fools an AI model expecting authentic data.
Tactics
Initial Access, Defense Evasion, Impact
ATT&CK cross-reference
No Enterprise ATT&CK cross-reference.
ATLAS mitigations & SSG coverage
AML.M0003
Predictive AI Model Hardening
Not addressed
Training-time model hardening
AML.M0006
Predictive AI Ensembles
Not addressed
Model architecture choice
AML.M0009
Predictive AI Multi-Sensor Fusion
Not addressed
Sensor and data-pipeline design
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.M0034
Deepfake Detection
Not addressed
Media forensics
AML.M0035
AI Red Team
Partial
SHAKEDOWN benchmark exercises containment; not a full red-team program
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.