Instructions to use hacnho/keras-textvec-flipud-batchswap-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use hacnho/keras-textvec-flipud-batchswap-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://hacnho/keras-textvec-flipud-batchswap-poc") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Keras TextVectorization flipud batch-order manipulation PoC
This repository contains a scanner-clean .keras proof of concept where a
malicious model patches TextVectorization.standardize to the exported Keras
function keras.ops.flipud.
Trigger:
KERAS_BACKEND=tensorflow python reproduce.py
Expected result:
- the control model predicts
[1, 0]for["approve transfer", "deny transfer"] - the malicious model predicts
[0, 1]for the same batch - single-row inference is unchanged
modelscanreportsNo issues found!
- Downloads last month
- 88
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support