AML.CS0058
Google Photos AI Model Extraction
- Type
- Exercise
- When
- 2025-03
- Actor, as ATLAS names it
- Not stated
- Target
- Google Photos Android App
- ATLAS attributes it to Skyld (security evaluation).
Techniques, in order
- 1Discover AI ArtifactsDiscovery · AML.T0007
- 2AI Artifact CollectionCollection · AML.T0035
- 3Exfiltration via Cyber MeansExfiltration · AML.T0025
- 4Full AI Model AccessAI Model Access · AML.T0044
- 5Craft Adversarial Data: White-Box OptimizationAI Attack Adaptation · AML.T0043.000
- 6Evade AI ModelImpact · AML.T0015
- 7External 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.