R-GAP
by JunyiZhu-AI
R-GAP: Recursive Gradient Attack on Privacy [Accepted at ICLR 2021]
AI summary
Gradient attack tool
A tool to demonstrate and analyze attacks on private data in machine learning models using gradients
- stars
- 34
- forks
- 2
- watching
- 2
Similar projects
Found by comparing what the projects do, not just their names.
Reconnaissance tool
Automates reconnaissance to identify potential attack surfaces of a target network
Attack framework
An adversarial attack framework on large vision-language models
Gradient leakage fix
This project presents an improved method to extract accurate private training data from publicly shared gradients in distributed learning systems.
Gradient Attack Method
Researchers develop an attack method to measure the effectiveness of federated learning privacy defenses by generating leakage in gradients
Gradient calculator
An autograd engine for textual gradients using large language models to backpropagate gradients.
Gradient inversion vulnerability fix
An implementation of a method to invert gradients in federated learning to potentially reveal sensitive client data
Attack framework
An attack framework to manipulate the output of large language models and vision-language models
Gradient extraction toolkit
This is a research project that extracts text from gradients with language model priors using deep learning techniques.
Gradient generator
A tool to generate linear web gradients with a user interface.
Robustness tester
A toolbox for researching and evaluating robustness against attacks on machine learning models
Federated Learning Vulnerability Framework
A framework for analyzing and exploiting vulnerabilities in federated learning models using surrogate model attacks
Model inversion attack
This implementation allows an attacker to directly obtain user data from federated learning gradient updates by modifying the shared model architecture.
Adversarial examples generator
A tool for generating adversarial examples to attack text classification and inference models
Robust network trainer
Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques.
Fraud detector
Develops and evaluates machine learning models for detecting financial fraud
