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 may manipulate an AI model's weights to change it's behavior or performance, resulting in a poisoned model. Adversaries may poison a model by directly manipulating its weights, training the model on poisoned data, further fine-tuning the model, or otherwise interferin…
Tactics
AI Attack Adaptation, Persistence
ATT&CK cross-reference
No Enterprise ATT&CK cross-reference.
ATLAS mitigations & SSG coverage
AML.M0005
Control Access to AI Models and Data at Rest
Not addressed
Data-at-rest infrastructure control
AML.M0007
Sanitize Training Data
Not addressed
Training-data curation
AML.M0008
Validate AI Model
Not addressed
Model evaluation practice
AML.M0013
Code Signing
Partial
Published rulesets are signed and transparency-logged; does not sign models
AML.M0025
Maintain AI Dataset Provenance
Not addressed
Dataset provenance tracking
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.