gradient_disaggregation
Federated Learning Reverser
An algorithm that breaks secure aggregation protocols in federated learning by recovering individual model updates from aggregated sums
14 stars
1 watching
0 forks
Language: Python
last commit: about 1 year ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 gaoliang13/feddc | Federated learning algorithm that adapts to non-IID data by decoupling and correcting for local drift | 81 |
 ignavierng/notears-admm | An implementation of Bayesian network structure learning with continuous optimization for federated learning. | 10 |
 zoesgithub/fedreg | An algorithm to improve convergence rates and protect privacy in Federated Learning by addressing the catastrophic forgetting issue during local training | 26 |
 jonasgeiping/invertinggradients | An implementation of an algorithm to recover input data from gradient information in neural networks. | 276 |
 lins-lab/fedbr | An implementation of federated learning algorithm to reduce local learning bias and improve convergence on heterogeneous data | 25 |
 yamingguo98/fediir | An implementation of a federated learning algorithm that generalizes to out-of-distribution scenarios using implicit invariant relationships | 10 |
 buaa-cst/ilrg | Recovery method for Federated Learning datasets using gradients to estimate instance-wise batch label restoration | 5 |
 lkyddd/gradma | A framework for accelerating federated learning with memory-based acceleration and alleviation of catastrophic forgetting | 13 |
 mediabrain-sjtu/feddg-ga | This project presents a method for federated domain generalization with adjustment, allowing multiple models to learn from each other across different domains. | 43 |
 ml-postech/gradient-inversion-generative-image-prior | An implementation of a method to invert gradients in federated learning to potentially reveal sensitive client data | 39 |
 zhuohangli/ggl | Researchers develop an attack method to measure the effectiveness of federated learning privacy defenses by generating leakage in gradients | 58 |
 lhfowl/robbing_the_fed | This implementation allows an attacker to directly obtain user data from federated learning gradient updates by modifying the shared model architecture. | 23 |
| mediabrain-sjtu/fedgela | This project enables federated learning across partially class-disjoint data with curated bilateral curation. | 11 |
 zfancy/sfat | Combating heterogeneity in federated learning by combining adversarial training with client-wise slack during aggregation | 28 |
 shams-sam/fedoptim | An open-source project exploring Federated Learning model updates and their rank structure using data from various datasets. | 14 |