Study Group Om Explorers
This group aims to study and learn about differential privacy, federated learning and PySyft.
Link to Study Group blog: https://zumrutmuftuoglu.github.io/OM-Study-Group/
Please see instructions_write_blog_post.md in the repo on instructions on how to write a blog post on the Study Group blog.
Join OpenMined
Resources: Differential Privacy
Thank you Professor Joseph Near for sharing your notes with us about data privacy!
- Data privacy notes
- Book: The Algorithmic Foundations of Differential
- Book: Differential Privacy From Theory to Practice
- Book: Differantial Privacy and Applications
- PhD Thesis of Naoise Holohan: Mathematical Foundations of Differantial Privacy
- Udacity course: Secure & Private AI
- Intro to DP Presentation by @Zumi-12/04/20
- Use cases of Differential Privacy and Federated Learning by @Ria
- Differential_Privacy_Toolkit_Idea
Secure & Private AI Google Colab notebooks by @Ria
- Udacity course DP Session 1 notebook
- Udacity course DP Session 1 Completed notebook
- Udacity course FL Session 2 notebook
- Udacity course FL Session 2 completed notebook
Blog
Topics to discuss
Join our study group
Sign up HERE
Resources: PySyft (OpenMined Tutorials)
Tutorials from OpenMined can be found here.
Part | Tutorial | Link |
---|---|---|
1 | The Basic Tools of Private Deep Learning | Part 01 |
2 | Intro to Federated Learning | Part 02 |
3 | Advanced Remote Execution Tools | Part 03 |
4 | Federated Learning with Model Averaging | Part 04 |
5 | Welcome to the Sandbox | Part 05 |
6 | Federated Learning on MNIST using a CNN | Part 06 |
7 | Federated Learning with FederatedDataset | Part 07 |