Metadata-Version: 2.4
Name: fal-framework
Version: 0.1.0
Summary: Federated Adversarial Learning framework.
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: adversarial-robustness-toolbox
Requires-Dist: flwr
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-learn
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: tqdm
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Provides-Extra: viz
Requires-Dist: matplotlib; extra == "viz"
Requires-Dist: seaborn; extra == "viz"

# FAL Framework

Federated Adversarial Learning framework for running federated learning experiments with clean, adversarial, and mixed training modes.

## Install

```bash
pip install fal-framework
```

## Use
```python

from sklearn.linear_model import LogisticRegression
from fal import FAL

fal = FAL(
    dataset="wine",
    model=LogisticRegression(max_iter=1000),
    trainer_type="clean",
    metrics=["accuracy", "f1"],
    num_clients=3,
    num_rounds=3,
    fl_algorithm="fedavg",
)

result = fal.run()
```
