A Comparative Study of Gradient Clipping Techniques in DP-SGD
-
Updated
May 10, 2024 - Python
A Comparative Study of Gradient Clipping Techniques in DP-SGD
DSPLab@UMich-Dearborn Website
Distributed DP-Helmet: Scalable Differentially Private Non-interactive Averaging of Single Layers
O objetivo deste projeto de iniciação científica é estudar a área de Privacy Preserving Machine Learning (PPML), que se dedica a encontrar soluções para realizar aprendizado de máquina de forma segura e preservando a privacidade dos dados.
Birhanu Eshete is an Associate Professor of Computer Science at the University of Michigan, Dearborn. His main research focus is in trustworthy machine learning with emphasis on security, safety, privacy, interpretability, fairness, and the dynamics thereof. He also studies online cybercrime and advanced and persistent threats (APTs).
Trustworthy AI/ML course by Professor Birhanu Eshete, University of Michigan, Dearborn.
Privacy Preserving Neural Networks (PPNN): Repo for Capstone Project at Ashoka
A more detailed description on the HPE Swarm Learning Installation guide. Official repo can be viewed on the url below:
This repository contains personal notes and summaries on Secure and Private AI
Python Privacy framework
Privacy-Preserving Multi-task Learning - Paper published at 2018 IEEE ICDM. Reference - K. Liu, N. Uplavikar, W. Jiang and Y. Fu, "Privacy-Preserving Multi-task Learning," 2018 IEEE International Conference on Data Mining (ICDM), Singapore, 2018, pp. 1128-1133, doi: 10.1109/ICDM.2018.00147.
Website for Privacy Engineering Program at CMU
A numpy-like wrapper around PALISADE library for the intersection of Homomorphic Encryption and Machine Learning
(in development) Home assistant custom component aiming to help self-consumers optimize their energy use in local and private manner.
Implementation of the PPDT in the paper "Enhanced Outsourced and Secure Inference for Tall Sparse Decision Trees"
This is the repository for Project of COMP 530 Data Privacy and Security course given by Emre Gursoy at Koc University. Code is written by Esad Simitcioglu, Arman Torikoglu, and Alireza Khodaie
Data anonymization
Implementation of privacy-preserving SVM assuming public model private data scenario
Implementation of the Heflp, a framework enabling practical and overflow-safe federated learning.
FedAnil+ is a novel lightweight, and secure Federated Deep Learning Model to address non-IID data, privacy concerns, and communication overhead. This repo hosts a simulation for FedAnil+ written in Python.
Add a description, image, and links to the privacy-preserving-machine-learning topic page so that developers can more easily learn about it.
To associate your repository with the privacy-preserving-machine-learning topic, visit your repo's landing page and select "manage topics."