|
@@ -0,0 +1,20 @@
|
|
|
|
|
+# aDPtorch
|
|
|
|
|
+
|
|
|
|
|
+An **advanced Differential Privacy** library for *pyTorch*, based on [opacus](https://github.com/pytorch/opacus).
|
|
|
|
|
+
|
|
|
|
|
+## Current Features
|
|
|
|
|
+
|
|
|
|
|
+- **privacy_engine_xl**
|
|
|
|
|
+ - additional noise distributions
|
|
|
|
|
+ - Gauss (Normal)
|
|
|
|
|
+ - Laplace
|
|
|
|
|
+ - Exponential
|
|
|
|
|
+ - server side noise generation function
|
|
|
|
|
+
|
|
|
|
|
+## License
|
|
|
|
|
+
|
|
|
|
|
+This repository is licensed under the [Apache License 2.0](LICENSE.md), as some of the code is derived from [opacus](https://github.com/pytorch/opacus).
|
|
|
|
|
+
|
|
|
|
|
+This repo contains a [markdown](LICENSE.md) and a [text](LICENSE-2.0.txt) version of the license.
|
|
|
|
|
+
|
|
|
|
|
+In case of any inconstancies refer to the [license's website](http://www.apache.org/licenses/).
|
