Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/lee-man/federated-learning

Related material on Federated Learning
https://github.com/lee-man/federated-learning

Last synced: 27 days ago
JSON representation

Related material on Federated Learning

Awesome Lists containing this project

README 

        
# Federated Learning

**Related concepts**: Differential privacy, Multi-Party Computation, Collaborative Learning. 



So far, the list is ordered randomly, without specific rules, which will be improved in future.

## Paper

1. - [x] **How To Backdoor Federated Learning**

[link](https://arxiv.org/abs/1807.00459);

[code](https://github.com/ebagdasa/backdoor_federated_learning)



1. - [ ] **Federated Learning: Strategies for Improving Communication Efficiency**

[link](https://arxiv.org/abs/1610.05492)



1. - [ ] **Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning**

[link](https://dl.acm.org/citation.cfm?id=3134012)



1. - [x] **Communication-Efficient Learning of Deep Networks from Decentralized Data** from *Google* 2016. The term *Federated Learning* was first used in this paper. [link](https://arxiv.org/abs/1602.05629)



1. **A Generic Framework for Privacy Preserving Peep Pearning** A detailed explanation of PySyft. [link](https://arxiv.org/abs/1811.04017)



1. - [x] **Federated Machine Learning: Concept and Applications** from *Qiang Yang*, etc. [link](https://arxiv.org/abs/1902.04885)



1. **Federated Learning for Mobile Keyboard Prediction** by *Google*. [link](https://arxiv.org/abs/1811.03604)



1. **Federated Optimization: Distributed Machine Learning for On-Device Intelligence** from *Google*. [link](https://arxiv.org/abs/1610.02527)



1. **Towards Federated Learning at Scale: System Design** from *Google*. [link](https://arxiv.org/abs/1902.01046)



1. **SecureML: A system for Scalable Privacy-Perserving Machine Learning** related to **Multi-party Computation**. [link](https://ieeexplore.ieee.org/abstract/document/7958569)



1. **Learning Differentially Private Recurrent Language Models** combine differentially private and federated learning. [link](https://arxiv.org/abs/1710.06963)



1. - [ ] **Practical Secure Aggregation for Privacy-Preserving Machine Learning**, secure aggregation to protect model from inference attack, from *Google*. [link](https://dl.acm.org/citation.cfm?id=3133982)



1. **Deep Learning with Differential Privacy** from *Google*. [link](https://dl.acm.org/citation.cfm?id=2978318)



1. **Privacy-Preserving Deep Learning**, introduced synchronized SGD. [link](https://dl.acm.org/citation.cfm?id=2813687)



1. **Exploiting Unintended Feature Leakage in Collaborative Learning**, an attack method related to membership inference, from *UCL* and *Cornell*. [link](https://arxiv.org/abs/1805.04049); [code](https://github.com/csong27/property-inference-collaborative-ml)



1. **Membership Inference Attacks Against Machine Learning Models** an paper on membership inference attack, from *Cornell* and etc. [link](https://ieeexplore.ieee.org/abstract/document/7958568); [code](https://github.com/csong27/membership-inference)



## Blog and Tutorial

1. **Federated Learning: Collaborative Machine Learning without Centralized Training Data** from *Google AI Blog*.

[link](https://ai.googleblog.com/2017/04/federated-learning-collaborative.html)



1. **Private AI — Federated Learning with PySyft and PyTorch** from *André Macedo Farias*. [link](https://towardsdatascience.com/private-ai-federated-learning-with-pysyft-and-pytorch-954a9e4a4d4e)



1. **An Overview of Federated Learning** from *Basil Han*. This blog introduces some challenges of federated learning, including *Inference Attack* and *Model Poisoning*.[link](https://medium.com/datadriveninvestor/an-overview-of-federated-learning-8a1a62b0600d)



1. **Federated Learning in 10 lines of PyTorch and PySyft** from *OpenMined*. [link](https://blog.openmined.org/upgrade-to-federated-learning-in-10-lines/)



1. **An Open Framework for Secure and Privated AI** from *ODSC*. [link](https://medium.com/@ODSC/an-open-framework-for-secure-and-private-ai-96c1891a4b)



1. **A Brief Introduction to Differential Privacy** from *Georgian Partners*. [link](https://medium.com/georgian-impact-blog/a-brief-introduction-to-differential-privacy-eacf8722283b)



1. **A beginners Guided to Federated Learning** from *Dr. Santanu Bhattacharya*. [link](https://hackernoon.com/a-beginners-guide-to-federated-learning-b29e29ba65cf).

	> Federated Learning was born at the intersection of on-device AI, blockchain, and edge computing/IoT.



1. **Federated Learning: The Future of Distributed Machine Learning** from *Synced*. [link](https://medium.com/syncedreview/federated-learning-the-future-of-distributed-machine-learning-eec95242d897)



1. *Important* **Federated Learning** an online comic from *Google AI*. [link](https://federated.withgoogle.com/)



1. **Under The Hood of The Pixel 2: How AI Is Supercharging Hardware** from *Google*. [link](https://ai.google/stories/ai-in-hardware/)



## Tool

1. **PySyft** [Github](https://github.com/OpenMined/PySyft)



1. **Tensorflow Federated** [link](https://www.tensorflow.org/federated); [Github](https://github.com/tensorflow/federated)



## MOOC

1. **Secure and Private AI** [Udacity](https://classroom.udacity.com/courses/ud185)