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.T0024.002 Partial Sub-technique of AML.T0024

Extract AI Model

Adversaries may extract a functional copy of a private model. By repeatedly querying the victim's [AI Model Inference API Access](/techniques/AML.T0040), the adversary can collect the target model's inferences into a dataset.

Tactics

Exfiltration

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.M0004 Limit AI Service Query Volume and Rate Partial Usage metering per device; not a general-purpose rate limiter

AML.M0024 AI Telemetry Logging Partial Detective control: records every governed call; does not block it

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.