UTC

AML.CS0013

Backdoor Attack on Deep Learning Models in Mobile Apps

Type
Exercise
When
2021-01-18
Actor, as ATLAS names it
Yuanchun Li, Jiayi Hua, Haoyu Wang, Chunyang Chen, Yunxin Liu
Target
ML-based Android Apps
Techniques, in order
  1. 1Search Application RepositoriesReconnaissance · AML.T0004
  2. 2Acquire Public AI Artifacts: ModelsResource Development · AML.T0002.001
  3. 3Full AI Model AccessAI Model Access · AML.T0044
  4. 4Develop Capabilities: Adversarial AI AttacksResource Development · AML.T0017.000
  5. 5Manipulate AI Model: Modify AI Model ArchitecturePersistence · AML.T0018.001
  6. 6Verify AttackAI Attack Adaptation · AML.T0042
  7. 7Supply Chain Compromise: Model RepositoryInitial Access · AML.T0010.003
  8. 8Craft Adversarial Data: Insert Backdoor TriggerAI Attack Adaptation · AML.T0043.004
  9. 9Physical Environment AccessAI Model Access · AML.T0041
  10. 10Evade AI ModelImpact · AML.T0015
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.