invertinggradients
Gradient recovery
An implementation of an algorithm to recover input data from gradient information in neural networks.
Algorithms to recover input data from their gradient signal through a neural network
272 stars
3 watching
71 forks
Language: Jupyter Notebook
last commit: over 1 year 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 |
 gdisag/gradient_disaggregation | An algorithm that breaks secure aggregation protocols in federated learning by recovering individual model updates from aggregated sums | 14 |
 buaa-cst/ilrg | Recovery method for Federated Learning datasets using gradients to estimate instance-wise batch label restoration | 5 |
 johnkorzhuk/grabient | A tool to generate linear web gradients with a user interface. | 1,990 |
 pkmr06/pytorch-smoothgrad | PyTorch implementation of a technique to improve the interpretability of deep learning models by adding noise to the gradients | 167 |
 git-disl/stdlens | A framework designed to protect federated learning models from hijacking attacks by identifying and removing compromised client gradients | 7 |
 springdaisy/gbdt | An implementation of Gradient Boosted Decision Trees with sparse output for high-dimensional data | 0 |
 lancopku/meprop | A technique to simplify backpropagation in neural networks by selectively computing only the most relevant gradients | 110 |
 ankurtaly/integrated-gradients | An attribution method for deep networks, attributing predictions to input features | 598 |
 gbdt-pl/gbdt-pl | An implementation of a gradient boosting algorithm with piece-wise linear regression trees for efficient machine learning model training | 149 |
 zou-group/textgrad | An autograd engine for textual gradients using large language models to backpropagate gradients. | 1,821 |
 siavashbigdeli/dmsp | A MATLAB implementation of an image restoration algorithm based on a deep mean-shift prior | 33 |
 amosgropp/igr | An algorithm for learning implicit signed distance representations from point clouds to reconstruct 3D surfaces. | 399 |
 hariofspades/gradient-artist | A library for applying gradient effects to images in Android applications | 49 |
 delta2323/gb-gnn | Analyzes and optimizes the performance of graph neural networks using gradient boosting and various aggregation models. | 13 |