Dopamine: Differentially Private Federated Learning on Medical Data (AAAI - PPAI)
-
Updated
Feb 9, 2025 - Python
8000
Dopamine: Differentially Private Federated Learning on Medical Data (AAAI - PPAI)
Securing Collaborative Medical AI by Using Differential Privacy
Easy-to-use utilities to build privacy-preserving AI.
Code for the paper "PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning" by L. Corbucci, M. A. Heikkilä, D.S. Noguero, A. Monreale, N. Kourtellis.
Building an AI model for chest X-ray under patient privacy guarantees
Hands-on part of the Federated Learning and Privacy-Preserving ML tutorial given at VISUM 2022
A differentially private spiking neural network with temporal enhanced pooling
A Comparative Study of Gradient Clipping Techniques in Differentially Private Stochastic Gradient Descent (DP-SGD)
In this project we add differential privacy into an openset recognizer.to implement DP we use opacus library.
Intrusion Detection with Differential Privacy using Opacus on the UNSW-NB15 dataset
Implementation of Opacus DP in Flower.
Implement differentially-private SGD on MLP classifier. Tested on MNIST dataset. For large privacy (ε), accuracy% decreases (down 97% --> 91%).
Add a description, image, and links to the opacus topic page so that developers can more easily learn about it.
To associate your repository with the opacus topic, visit your repo's landing page and select "manage topics."