Instructions to use zamaanahmed/mfv-keras-native-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use zamaanahmed/mfv-keras-native-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://zamaanahmed/mfv-keras-native-poc") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
tags: [security-research, mfv, scanner-bypass, keras]
|
| 4 |
+
---
|
| 5 |
+
# PMML (.keras) MFV PoC — Authorized Security Research
|
| 6 |
+
|
| 7 |
+
Authorization: huntr.com / Protect AI MFV bug bounty program. Local venv. Responsible disclosure.
|
| 8 |
+
|
| 9 |
+
## Files
|
| 10 |
+
- `malicious.keras` — bzip2 joblib payload, bypasses picklescan 1.0.4 + modelscan 0.8.8
|
| 11 |
+
- `README.md` — this file
|