Metadata-Version: 2.4
Name: isage-privacy
Version: 0.1.0.2
Summary: SAGE Privacy Framework - Differential privacy, federated learning, machine unlearning, PII detection
Author-email: IntelliStream Team <shuhao_zhang@hust.edu.cn>
License-Expression: MIT
Project-URL: Homepage, https://github.com/intellistream/sage-privacy
Project-URL: Repository, https://github.com/intellistream/sage-privacy
Keywords: privacy,differential-privacy,federated-learning,machine-unlearning,PII,LLM,AI
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.20.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: typing-extensions>=4.0.0
Requires-Dist: isage-libs>=0.2.0
Provides-Extra: full
Provides-Extra: dev
Requires-Dist: isage-privacy[full]; extra == "dev"
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: ruff>=0.4.0; extra == "dev"

# sage-privacy

Privacy protection algorithms for SAGE, including differential privacy and machine unlearning.

**PyPI Package**: `isage-privacy`

## Boundary

- Root package (`sage_libs.sage_privacy`) exposes only stable metadata and explicit registration API.
- Research implementations are accessed from subpackages:
	- `sage_libs.sage_privacy.dp`
	- `sage_libs.sage_privacy.unlearning`
- No root-level re-export of concrete research implementations.

## Installation

```bash
pip install isage-privacy
```

## Usage

```python
from sage_libs.sage_privacy import register_to_sage
from sage_libs.sage_privacy.dp import GaussianMechanism
from sage_libs.sage_privacy.unlearning import GradientAscentUnlearner

register_to_sage()

mechanism = GaussianMechanism(epsilon=1.0)
unlearner = GradientAscentUnlearner()
```

## License

MIT
