Ready to deep dive into the Federated Learning journey with selected state-of-the-art and valuable readings!

🎯 Intro

Blog

1. Google – Federated Learning: Collaborative Machine Learning without Centralized Training Data – April 6, 2017
2. Comic – https://federated.withgoogle.com/
3. https://medium.com/@ODSC/what-is-federated-learning-99c7fc9bc4f5
4. https://towardsdatascience.com/introduction-to-federated-learning-and-challenges-ea7e02f260ca
5. https://towardsdatascience.com/how-federated-learning-is-going-to-revolutionize-ai-6e0ab580420f

Initial papers

1. Practical Secure Aggregation for Privacy-Preserving Machine Learning – Google, 2016
2. Federated Learning: Strategies for Improving Communication Efficiency – 2016
3. Communication-Efficient Learning of Deep Networks from Decentralized Data – 2017

Talk – Seminar

1. Federated Learning One World Seminar – https://sites.google.com/view/one-world-seminar-series-flow/archive
2. Coursera – https://www.coursera.org/learn/advanced-deployment-scenarios-tensorflow

📜 Survey

1. Advances and Open Problems in Federated Learning
2. A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
3. A Systematic Literature Review on Federated Machine Learning: From A Software Engineering Perspective
4. Federated Learning for 6G Communications: Challenges, Methods, and Future Directions
5. Threats to Federated Learning: A Survey
6. Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art
7. Federated Learning: Challenges, Methods, and Future Directions
8. Federated Learning in Mobile Edge Networks: A Comprehensive Survey
9. Federated Machine Learning: Concept and Applications
10. Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective
11. A Review of Privacy-preserving Federated Learning for the Internet-of-Things

📦 System design – frameworks – libraries

1. PySyft – A library for computing on data you do not own and cannot see
   • Github: https://github.com/OpenMined/PySyft
2. Tensorflow Federated
   • Website: https://www.tensorflow.org/federated
3. FedML: A Research Library and Benchmark for Federated Machine Learning
   • Website: https://fedml.ai/
4. Flower – A Friendly Federated Learning Framework
   • Github: https://github.com/adap/flower
5. Federated Learning Pytorch
   • Github: https://github.com/AshwinRJ/Federated-Learning-PyTorch
6. PrivacyFL: A simulator for privacy-preserving and secure federated learning.
7. Towards Federated Learning at Scale: System Design

💻 Models and Applications

1. DIOT: A Federated Self-learning Anomaly Detection System for IoT
2. MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets.
3. (GAN) Federated Generative Adversarial Learning
4. Efficient Privacy-Preserving Edge Computing Framework for Image Classification

🛡️ Security and Privacy

Overview

An Overview of Federated Deep Learning Privacy Attacks and Defensive Strategies. 2020-04-01 Citation: 0

Backdoor Attacks

Awesome Backdoor Learning List: https://github.com/THUYimingLi/backdoor-learning-resources
Survey: Backdoor Learning – a survey

1. AISTATS 2020 – How To Backdoor Federated Learning ✅ ⭐️⭐️
   • Github: https://github.com/ebagdasa/backdoor_federated_learning
   • Conf: http://proceedings.mlr.press/v108/bagdasaryan20a.html
   • Supplementary PDF: http://proceedings.mlr.press/v108/bagdasaryan20a/bagdasaryan20a-supp.pdf
2. Blind Backdoors in Deep Learning Models (2021) ✅ ⭐️⭐️
   • Github: https://github.com/ebagdasa/backdoors101
3. ICLR 2020 – DBA: Distributed Backdoor Attacks against Federated Learning
   • Github: https://github.com/AI-secure/DBA
4. NeurIPS 2019 – Can You Really Backdoor Federated Learning?
5. Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
6. NeurIPS 2020 Submission: Backdoor Attacks on Federated Meta-Learning

Data Poisoning

1. Data Poisoning Attacks Against Federated Learning Systems ✅ ⭐️⭐️
   • Github: https://github.com/git-disl/DataPoisoning_FL
2. Data Poisoning Attacks on Federated Machine Learning
3. Poisoning Attacks with Generative Adversarial Nets
4. Poisoning Attack in Federated Learning using Generative Adversarial Nets

Model Poisoning

1. ICML 2019 – Analyzing Federated Learning through an Adversarial Lens ✅ ⭐️⭐️⭐️ – Citation: 165 – Highlight: client attack
2. USS 2020 – Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

Inference Attacks

1. Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning

Free-rider Attacks

1. NeurIPS 2020 – Free-rider Attacks on Model Aggregation in Federated Learning
2. Free-riders in Federated Learning: Attacks and Defenses

Leakage

1. Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning. ACM CCS 2017. 2017-02-14 Citation: 284
2. Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning. INFOCOM 2019 Citation: 56 Highlight: server-side attack
3. A Framework for Evaluating Gradient Leakage Attacks in Federated Learning. 2020-04-22 Researcher: Wenqi Wei, Ling Liu, GaTech
4. Quantification of the Leakage in Federated Learning. 2019-10-12 Citation: 1

Privacy

1. Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices
2. Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning. 2018-12-03 Citation: 46
3. Inverting Gradients – How easy is it to break privacy in federated learning? 2020-03-31 Citation: 3
   • Github: https://github.com/JonasGeiping/invertinggradients

Defense

1. Mitigating Sybils in Federated Learning Poisoning. 2018-08-14. RAID 2020 Citation: 41 Highlight: defense
   • Github: https://github.com/DistributedML/FoolsGold
2. RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasets, AAAI 2019 Citation: 34
   • Github: https://github.com/Liepill/RSA-Byzantine
3. Towards Realistic Byzantine-Robust Federated Learning. 2020-04-10
4. FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications. 2020-06-28
5. Learning to Detect Malicious Clients for Robust Federated Learning. 2020-02-01
6. Robust Aggregation for Federated Learning. 2019-12-31 Citation: 9
7. Towards Deep Federated Defenses Against Malware in Cloud Ecosystems. 2019-12-27
8. Attack-Resistant Federated Learning with Residual-based Reweighting. 2019-12-23
9. Robust Federated Learning with Noisy Communication. 2019-11-01 Citation:
10. Abnormal Client Behavior Detection in Federated Learning. 2019-10-22 Citation: 3
11. Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging. 2019-09-11
12. An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning. 2019-08-22
13. Ensemble Distillation for Robust Model Fusion in Federated Learning
    • https://github.com/epfml/federated-learning-public-code/tree/master/codes/FedDF-code

Other Resources and References

• Awesome Federated Learning: https://github.com/chaoyanghe/Awesome-Federated-Learning (main reference)
• Google AI: https://ai.google/
• Deep AI: https://deepai.org/
• Papers with Codes: https://paperswithcode.com/task/federated-learning