Image Classification
Keras
mnist
model-security
responsible-disclosure
model-format-vulnerability
output-manipulation
backdoor
safe-mode
Instructions to use AM-Core/mnist-native-keras-output-manipulation-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use AM-Core/mnist-native-keras-output-manipulation-poc with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://AM-Core/mnist-native-keras-output-manipulation-poc") - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_dataset": "MNIST", | |
| "original_label": 5, | |
| "clean_predicted_class": 5, | |
| "triggered_predicted_class": 7, | |
| "target_class": 7, | |
| "output_manipulated": true, | |
| "safe_mode_true_load_successful": true | |
| } |