UTC

AML.CS0019

PoisonGPT

Type
Exercise
When
2023-07
Actor, as ATLAS names it
Not stated
Target
HuggingFace Users
Techniques, in order
  1. 1Acquire Public AI Artifacts: ModelsResource Development · AML.T0002.001
  2. 2Manipulate AI Model: Poison AI ModelAI Attack Adaptation · AML.T0018.000
  3. 3Verify AttackAI Attack Adaptation · AML.T0042
  4. 4Publish Poisoned AI Artifacts: ModelsResource Development · AML.T0115.001
  5. 5Supply Chain Compromise: Model RepositoryInitial Access · AML.T0010.003
  6. 6Erode AI Model IntegrityImpact · AML.T0031
  7. 7External Harms: Reputational HarmImpact · AML.T0048.001
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.