This repository is used to summarize the latest research progress of privacy-preserving machine learning (PPML)，privacy-preserving deep learning (PPDL)
Some related github repositories
-
Deep Learning with Differential Privacy - arXiv 2016
-
Differentially Private Federated Learning: A Client Level Perspective - arXiv 2016
-
Learning differentially private recurrent language models - ICLR 2018
The PATE ('Private Aggregation of Teacher Ensembles') framework was introduced by Papernot et al. Strictly speaking, PATE is one of implementations of differential privacy, this framework enables model-agnostic training that provably provides differential privacy of the training dataset.
-
Scalable Private Learning with PATE - ICLR 2018
-
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data - ICLR 2017
- SHE: A Fast and Accurate Deep Neural Network for Encrypted Data - NeurIPS 2019
- Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference - arXiv 2018
- The AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data with GPUs - arXiv 2018
- CryptoDL: Deep Neural Networks over Encrypted Data - arXiv 2017
- Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption - arXiv 2017 (Apply additively homomorphic encryption algorithm to Federated Learning)
- CryptoNets: applying neural networks to encrypted data with high throughput and accuracy - ICML 2016