Keras Equalization trigger PoC
Benign security research PoC for a Keras Native model-file trigger backdoor.
Files:
equalization_control.kerasequalization_trigger.kerasreproduce.py
Tested with keras==3.15.0 and tensorflow-cpu==2.19.0.
Trigger: a 4x4 sparse checkerboard at image[::2, ::2].
Run:
KERAS_BACKEND=tensorflow python reproduce.py
Expected result:
- control model score for trigger: near
0 - malicious model score for trigger: near
1 - malicious model scores for listed non-trigger probes: below
0.001
Scanner posture recorded locally:
modelscan 0.8.8:No issues foundpicklescan 0.0.31:Infected files: 0,Dangerous globals: 0
- Downloads last month
- 150
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support