FebriantiW / Homomorphic-Encryption-and-Federated-Learning-based-Privacy-Preserving-CNN-Training-
Medical data is often highly sensitive in terms of data privacy and security concerns. Federated learning, one type of machine learn- ing techniques, has been started to use for the improvement of the privacy and security of medical data. In the federated learning, the training data is distributed across multiple machines, and the learning proce…
☆18Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Homomorphic-Encryption-and-Federated-Learning-based-Privacy-Preserving-CNN-Training-
- Preserve data privacy with k-anonymity (samarati & mondrian), differential privacy, federated learning, paillier homomorphic encryption, …☆57Updated 2 years ago
- FedAvg code with privacy protection function, the application of Paillier homomorphic encryption algorithm and differential privacy, diff…☆106Updated last month
- FedShare: Secure Aggregation based on Additive Secret Sharing in Federated Learning☆16Updated last year
- A foundational platform that primarily shares federated learning, differential privacy content☆19Updated 2 weeks ago
- Privacy-Preserving Convolutional Neural Networks using Homomorphic Encryption☆73Updated 3 months ago
- Differential priavcy based federated learning framework by various neural networks and svm using PyTorch.☆30Updated 3 years ago
- SAFEFL: MPC-friendly Framework for Private and Robust Federated Learning☆29Updated last year
- Privacy-Preserving Deep Learning via Additively Homomorphic Encryption☆67Updated 3 years ago
- Chain-PPFL: A Privacy-Preserving Federated Learning Framework based on Chained SMC☆30Updated 4 years ago
- personal implementation of secure aggregation protocol☆42Updated 9 months ago
- Privacy-preserving federated learning is distributed machine learning where multiple collaborators train a model through protected gradi…☆27Updated 3 years ago
- Source code for MLSys 2022 submission "LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning"☆23Updated 3 years ago
- Privacy Preserving Federated Learning on a Deep Neural Network☆8Updated 4 years ago
- [arXiv'21] Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning☆18Updated 10 months ago
- IEEE TIFS'20: VeriFL: Communication-Efficient and Fast Verifiable Aggregation for Federated Learning☆22Updated 2 years ago
- Implementation of Shuffled Model of Differential Privacy in Federated Learning." AISTATS, 2021.☆17Updated 2 years ago
- Code for the CCS'22 paper "Federated Boosted Decision Trees with Differential Privacy"☆43Updated last year
- Differential priavcy based federated learning framework by various neural networks and svm using PyTorch.☆43Updated last year
- Homomorphic Encryption and Federated Learning based Privacy-Preserving☆59Updated last year
- Multi‐key homomorphic encryption based on MKCKKS☆17Updated 2 years ago
- MPC Secure Multiparty Computation. A three-party secret-sharing-based vertical federated learning setting. The data are vertically parti…☆24Updated 5 years ago
- Federated Learning and Membership Inference Attacks experiments on CIFAR10☆19Updated 4 years ago
- Curated notebooks on how to train neural networks using differential privacy and federated learning.☆66Updated 3 years ago
- This is an implementation for paper "A Hybrid Approach to Privacy Preserving Federated Learning" (https://arxiv.org/pdf/1812.03224.pdf)☆21Updated 4 years ago
- Efficient and Straggler-Resistant Homomorphic Encryption for Heterogeneous Federated Learning☆15Updated last month
- An implementation of Secure Aggregation algorithm based on "Practical Secure Aggregation for Privacy-Preserving Machine Learning (Bonawit…☆81Updated 5 years ago
- Differentially Private Federated Learning on Heterogeneous Data☆59Updated 2 years ago
- Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization☆9Updated 3 years ago
- A simple Python implementation of a secure aggregation protocole for federated learning.☆34Updated last year
- Applying Laplace and exponential mechanisms to add random noise to data for differential privacy. Plotting MSE vs. epsilon.☆27Updated 4 years ago