Threat intelligence / Campaign

Google Photos AI Model Extraction

Skyld researchers analyzed the Google Photos Android application and recovered TensorFlow Lite models used by AI-powered photo editing and image analysis features. The researchers found models stored unencrypted in the application's assets, embedded in the native library, and encrypted on disk. They used static reverse engineering to locate TFLite artifacts and dynamic instrumentation with Frida to capture encrypted models after runtime decryption. The recovered models provided white-box access to proprietary Google Photos model artifacts.

Campaign

TypeCampaign

External ID—

First seen2026-08-14

Last seen2026-08-14

Confidence

—

Skyld researchers analyzed the Google Photos Android application and recovered TensorFlow Lite models used by AI-powered photo editing and image analysis features. The researchers found models stored unencrypted in the application's assets, embedded in the native library, and encrypted on disk. They used static reverse engineering to locate TFLite artifacts and dynamic instrumentation with Frida to capture encrypted models after runtime decryption. The recovered models provided white-box access to proprietary Google Photos model artifacts.

7 recorded

Relationships

uses

to AI Artifact Collection

Technique

uses

to AI Intellectual Property Theft

Technique

uses

to Discover AI Artifacts

Technique

uses

to Evade AI Model

Technique

uses

to Exfiltration via Cyber Means

Technique

uses

to Full AI Model Access

Technique

uses

to White-Box Optimization

Technique

1 external

References

mitre-atlas

AML.CS0058