Improved-Deep-Leakage-from-Gradients
Gradient leakage fix
This project presents an improved method to extract accurate private training data from publicly shared gradients in distributed learning systems.
The code for "Improved Deep Leakage from Gradients" (iDLG).
144 stars
5 watching
39 forks
Language: Python
last commit: over 3 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 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 |
 eth-sri/lamp | This is a research project that extracts text from gradients with language model priors using deep learning techniques. | 23 |
 ymjs-irfan/dp-fedsam | This repository provides an implementation of a differentially private federated learning algorithm designed to improve the robustness and performance of federated machine learning systems. | 41 |
 pkmr06/pytorch-smoothgrad | PyTorch implementation of a technique to improve the interpretability of deep learning models by adding noise to the gradients | 167 |
 junyizhu-ai/r-gap | A tool to demonstrate and analyze attacks on private data in machine learning models using gradients | 34 |
 zhuohangli/ggl | An attack implementation to test and evaluate the effectiveness of federated learning privacy defenses. | 57 |
 buaa-cst/ilrg | Recovery method for Federated Learning datasets using gradients to estimate instance-wise batch label restoration | 5 |
 jackqqwang/pfedhr | A Python project implementing a novel approach to high-performance feature learning and dimensionality reduction in deep neural networks | 7 |
 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 |
 dr-darryl-wright/noisy-labels-with-bootstrapping | An implementation of training deep neural networks on noisy labels with bootstrapping using Keras | 22 |
 tianhongdai/integrated-gradient-pytorch | A PyTorch implementation of attributing the impact of inputs on deep neural network outputs | 181 |
 tqchen/xgboost | An optimized distributed gradient boosting library for machine learning | 571 |
 pingqingsheng/lrt | An algorithm designed to robustly correct noisy labels in training data by iteratively refining the network's confidence and updating the loss function. | 21 |
| eth-sri/bayes-framework-leakage | Develops and evaluates a framework for detecting attacks on federated learning systems | 11 |
 zhanghang1989/pytorch-encoding | A Python framework for building deep learning models with optimized encoding layers and batch normalization. | 2,041 |