kenziyuliu / DP2
[ICLR 2023] Official JAX/Haiku implementation of the paper "Differentially Private Adaptive Optimization with Delayed Preconditioners"
☆16Updated last year
Related projects ⓘ
Alternatives and complementary repositories for DP2
- ☆13Updated last year
- Private Adaptive Optimization with Side Information (ICML '22)☆16Updated 2 years ago
- [NeurIPS 2022] JAX/Haiku implementation of "On Privacy and Personalization in Cross-Silo Federated Learning"☆25Updated last year
- ☆79Updated 2 years ago
- [CCS 2021] "DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation" by Boxin Wang*, Fan Wu*, Yunhui Long…☆37Updated 2 years ago
- Official implementation of "Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective"☆55Updated last year
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆30Updated 2 years ago
- ☆55Updated 3 years ago
- ☆13Updated last year
- Federated Learning Framework Benchmark (UniFed)☆47Updated last year
- Code for Auditing DPSGD☆35Updated 2 years ago
- ☆53Updated last year
- R-GAP: Recursive Gradient Attack on Privacy [Accepted at ICLR 2021]☆34Updated last year
- Simplicial-FL to manage client device heterogeneity in Federated Learning☆21Updated last year
- ☆12Updated 3 years ago
- Federated Learning with Partial Model Personalization☆42Updated 2 years ago
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆70Updated 9 months ago
- ☆40Updated last year
- ☆15Updated 9 months ago
- This repo implements several algorithms for learning with differential privacy.☆102Updated last year
- ☆15Updated 2 years ago
- PyTorch for benchmarking communication-efficient distributed SGD optimization algorithms☆72Updated 3 years ago
- Papers related to federated learning in top conferences (2020-2024).☆66Updated last month
- ☆10Updated 2 years ago
- InstaHide: Instance-hiding Schemes for Private Distributed Learning☆50Updated 4 years ago
- ☆14Updated 10 months ago
- CRFL: Certifiably Robust Federated Learning against Backdoor Attacks (ICML 2021)☆71Updated 3 years ago
- Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent (ICLR 2021)☆20Updated 3 years ago
- FedDANE: A Federated Newton-Type Method (Asilomar Conference on Signals, Systems, and Computers ‘19)☆24Updated last year
- DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.☆25Updated 3 months ago