AML.CS0028
AI Model Tampering via Supply Chain Attack
- Type
- Exercise
- When
- 2023-09-26
- Actor, as ATLAS names it
- Not stated
- Target
- Private Container Registries
- ATLAS attributes it to Trend Micro (security evaluation).
Techniques, in order
- 1Search Application RepositoriesReconnaissance · AML.T0004
- 2Exploit Public-Facing ApplicationInitial Access · AML.T0049
- 3Discover AI ArtifactsDiscovery · AML.T0007
- 4Full AI Model AccessAI Model Access · AML.T0044
- 5External Harms: AI Intellectual Property TheftImpact · AML.T0048.004
- 6Manipulate AI Model: Poison AI ModelPersistence · AML.T0018.000
- 7Manipulate AI Model: Modify AI Model ArchitecturePersistence · AML.T0018.001
- 8Supply Chain Compromise: Container RegistryInitial Access · AML.T0010.004
- 9Evade AI ModelImpact · AML.T0015
How these attacks work
References
- Silent Sabotage: Weaponizing AI Models in Exposed Containers
- Exposed Container Registries: A Potential Vector for Supply-Chain Attacks
- Mining Through Mountains of Information and Risk: Containers and Exposed Container Registries
- The Growing Threat of Unprotected Container Registries: An Urgent Call to Action
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.