AML.CS0075
Model Distillation Campaigns Targeting Google AI Services
- Type
- Incident
- When
- 2025 to 2026
- Actor, as ATLAS names it
- Multiple unknown actors
- Target
- Google AI Services, including Gemini
Techniques, in order
- 1Compromise AccountsResource Development · AML.T0139
- 2Establish AccountsResource Development · AML.T0021
- 3Acquire Infrastructure: AI Service ProxiesResource Development · AML.T0008.005
- 4Valid AccountsInitial Access · AML.T0012
- 5Centralized AI Service Request RoutingDefense Evasion · AML.T0140
- 6LLM Prompt CraftingAI Attack Adaptation · AML.T0065
- 7Exfiltration via AI Inference APIExfiltration · AML.T0024
- 8Outputs from AI ModelsCollection · AML.T0135
- 9Replicate AI Model Behavior: Replicate Behavior from Model OutputsResource Development · AML.T0005.001
- 10External Harms: AI Intellectual Property TheftImpact · AML.T0048.004
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.