Instructions to use stuub/ACE-Keras-001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use stuub/ACE-Keras-001 with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://stuub/ACE-Keras-001") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
ModelScan Bypass โ Hidden Lambda in Keras Dense Layer Activation
Summary
Proof-of-concept .keras model file that achieves arbitrary code execution while evading ModelScan v0.8.8 detection entirely.
Reproduction
pip install keras tensorflow modelscan
# Step 1: Scan (reports clean)
modelscan scan --path model.keras
# Step 2: Load and run (executes code)
python3 -c "
import keras, numpy as np
keras.config.enable_unsafe_deserialization()
model = keras.models.load_model('model.keras')
model.predict(np.zeros((1,5)))
"
Files
model.kerasโ Malicious .keras file with hidden__lambda__in Dense activation
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support