Privacy preserving deep learning for PyTorch
PyVacy: Privacy Algorithms for PyTorch
PyVacy provides custom PyTorch opimizers for conducting deep learning in a differentially private manner. Basically TensorFlow Privacy, but for PyTorch.
pip install pyvacy
import torch from pyvacy import optim, analysis model = torch.nn.Sequential(...) optimizer = optim.DPSGD( l2_norm_clip=..., noise_multiplier=..., batch_size=..., lr=..., momentum=..., ) epsilon = analysis.moments_accountant( N=..., batch_size=... noise_multiplier=..., epochs=..., delta=..., ) for epoch in range(epochs): # do training as usual...
python tutorials/mnist.py Training procedure achieves (3.0, 0.00001)-DP [Epoch 1/60] [Batch 0/235] [Loss: 2.321049] [Epoch 1/60] [Batch 10/235] [Loss: 0.952795] [Epoch 1/60] [Batch 20/235] [Loss: 1.040896] ...
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size pyvacy-0.0.32.tar.gz (10.3 kB)||File type Source||Python version None||Upload date||Hashes View|