Soteria
Federated Learning Defense
An implementation of a defense against model inversion attacks in federated learning
Official implementation of "Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective"
55 stars
2 watching
9 forks
Language: Jupyter Notebook
last commit: over 1 year ago cvpr2021federated-learningmodel-inversion-attackprivacy
Related projects:
| Repository | Description | Stars |
|---|---|---|
 git-disl/lockdown | A backdoor defense system for federated learning, designed to protect against data poisoning attacks by isolating subspace training and aggregating models with robust consensus fusion. | 18 |
 dcalab-unipv/turning-privacy-preserving-mechanisms-against-federated-learning | This project presents an attack on federated learning systems to compromise their privacy-preserving mechanisms. | 8 |
 ai-secure/fedgame | An implementation of a game-theoretic defense against backdoor attacks in federated learning. | 6 |
 shenzebang/centaur-privacy-federated-representation-learning | A framework for Federated Learning with Differential Privacy using PyTorch | 13 |
| jeremy313/fl-wbc | A defense mechanism against model poisoning attacks in federated learning | 37 |
 haoyuzhao123/soteriafl | Numerical experiments for private federated learning with communication compression algorithms | 7 |
 deu30303/feddefender | A PyTorch implementation of an attack-tolerant federated learning system to train robust local models against malicious attacks from adversaries. | 10 |
 zju-diver/shapleyfl-robust-federated-learning-based-on-shapley-value | An implementation of a robust federated learning method based on Shapley value to defend against various data and model poisoning attacks | 19 |
 ksreenivasan/ood_federated_learning | Researchers investigate vulnerabilities in Federated Learning systems by introducing new backdoor attacks and exploring methods to defend against them. | 66 |
| ai-secure/dba | A tool for demonstrating and analyzing attacks on federated learning systems by introducing backdoors into distributed machine learning models. | 179 |
 sap-samples/machine-learning-diff-private-federated-learning | Simulates a federated learning setting to preserve individual data privacy | 365 |
 zlijingtao/ressfl | Develops techniques to improve the resistance of split learning in federated learning against model inversion attacks | 19 |
 zhuohangli/ggl | Researchers develop an attack method to measure the effectiveness of federated learning privacy defenses by generating leakage in gradients | 58 |
 wizard1203/vhl | A toolkit for federated learning with a focus on defending against data heterogeneity | 40 |
| ai-secure/crfl | This project presents a framework for robust federated learning against backdoor attacks. | 71 |