There are 1 repository under pysyft topic.
Detect anomalies in network traffic data using Federated Machine Learning technique.
SOON TO BE DEPRECATED - The TensorFlow bindings for PySyft
Integration of SplitNN for vertically partitioned data with OpenMined's PySyft
Credit Approval Classification Deep Learning Model using Differential Drivacy, Secure Multi-Party Computation, and Federated Learning
Material supporting the tutorial "Pursuing Privacy in Recommender Systems: The View of Users and Researchers from Regulations to Applications" held at the 15th ACM Conference on Recommender Systems in Amsterdam, Netherlands
Federated learning with homomorphic encryption enables multiple parties to securely co-train artificial intelligence models in pathology and radiology, reaching state-of-the-art performance with privacy guarantees.
Healthcare-Researcher-Connector Package: Federated Learning tool for bridging the gap between Healthcare providers and researchers
An implementation of Federated Learning using Pytorch and PySyft
A simple federated learning implementation on MNIST dataset using PySyft. Main goal of the project was to get used to the PySyft federated learning functionality instead of using traditional PyTorch features.
Demonstration of application of Distributed Computing in Federated Learning for our Semester-8 Course on Distributed and Cloud Computing
The project showcasing federated learning of model and testing on encrypted data and model
Project entry for the Secure and Private AI Challenge, hosted by Udacity and sponsored by Facebook (May - August, 2019)
Securing Collaborative Medical AI by Using Differential Privacy
Repo including all the daily updates of #60daysofudacity Udacity Challenge
Repo for project : smog detection project at Udacity Project Showcase
Implementations notebooks and scripts of secured and private ai scholarship challenge from facebook.
All Things Deep Learning Projects
Multi-Party Computation transforms data handling by decentralizing trust among multiple participants. This ensures that no single entity demands absolute trust. An advantage for companies in safeguarding data privacy: once data leaves the user's computer, it remains obscured from any single external entity.
A collection of research and survey papers of differential privacy and federated learning
:fire: Federated Learning Simplified with Frameworks
The premise of this challenge is to build a habit of practicing new skills by making a public commitment of practicing the topics of Secure and Private AI program every day for 60 days.
The workspace for the Secure and Private AI course on Udacity. https://www.udacity.com/course/secure-and-private-ai--ud185
Secure & Private AI Challenge Codes
Udacity Deep Learning, PyTorch, PySyft
This repository will help you to understand how Federated learning can be implemented on Pima Indians Diabetic Dataset. It involves the use of OpenMined tool called Pysyft and Pytorch for implementation.
Simple example of federated learning using torch ignite and pysyft