AML.CS0031
Malicious Models on Hugging Face
- Type
- Incident
- When
- 2025
- Actor, as ATLAS names it
- Unknown
- Target
- Hugging Face users
Techniques, in order
- 1Manipulate AI Model: Embed MalwareAI Attack Adaptation · AML.T0018.002
- 2Publish Poisoned AI Artifacts: ModelsResource Development · AML.T0115.001
- 3Corrupt AI ModelDefense Evasion · AML.T0076
- 4Supply Chain CompromiseInitial Access · AML.T0010
- 5User Execution: Unsafe AI ArtifactsExecution · AML.T0011.000
- 6Cyber Communication ChannelCommand and Control · AML.T0072
How these attacks work
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.