UTC

AML.CS0027

Organization Confusion on Hugging Face

Type
Exercise
When
2023-08-23
Actor, as ATLAS names it
threlfall_hax
Target
Hugging Face users
Techniques, in order
  1. 1Establish AccountsResource Development · AML.T0021
  2. 2ImpersonationDefense Evasion · AML.T0073
  3. 3Full AI Model AccessAI Model Access · AML.T0044
  4. 4External Harms: AI Intellectual Property TheftImpact · AML.T0048.004
  5. 5Manipulate AI Model: Embed MalwareAI Attack Adaptation · AML.T0018.002
  6. 6Publish Poisoned AI Artifacts: ModelsResource Development · AML.T0115.001
  7. 7Supply Chain Compromise: Model RepositoryInitial Access · AML.T0010.003
  8. 8User Execution: Unsafe AI ArtifactsExecution · AML.T0011.000
  9. 9MasqueradingDefense Evasion · AML.T0074
  10. 10Cyber Communication ChannelCommand and Control · AML.T0072
  11. 11Unsecured CredentialsCredential Access · AML.T0055
  12. 12Exfiltration via Cyber MeansExfiltration · AML.T0025
  13. 13Discover AI ArtifactsDiscovery · AML.T0007
  14. 14Obtain Capabilities: Adversarial AI Attack ImplementationsResource Development · AML.T0016.000
  15. 15Manipulate AI Model: Poison AI ModelAI Attack Adaptation · AML.T0018.000
  16. 16External HarmsImpact · AML.T0048
The full case study on MITRE ATLAS →

From MITRE ATLAS 2026.10 (Apache-2.0). ShieldMap lists who and what was involved and the techniques used, and links to ATLAS for the write-up; it does not copy the steps. Attribution is ATLAS's, not ShieldPi's.