kasramojallal1/FedMod
A lightweight, privacy-preserving Vertical Federated Learning framework using multi-server additive secret sharing for scalable, secure ML without heavy cryptography
Organizations with different datasets about the same customers can securely collaborate to build machine learning models without directly sharing sensitive information. This framework takes isolated datasets, builds a unified machine learning model (for tasks like predicting customer behavior or classifying data), and produces a model that performs as well as if all the data had been combined, but with enhanced privacy. This is for data scientists, machine learning engineers, and privacy officers in regulated industries like finance, healthcare, or government.
No commits in the last 6 months.
Use this if you need to train machine learning models using data from multiple sources, where sharing raw data is not permissible due to privacy concerns, but you still require high model accuracy and efficiency.
Not ideal if your organization can freely share and combine all datasets without any privacy or security restrictions, or if you need to train models where different organizations have different users, not different features of the same users.
Stars
8
Forks
—
Language
Python
License
—
Category
Last pushed
Jul 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kasramojallal1/FedMod"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
flwrlabs/flower
Flower: A Friendly Federated AI Framework
JonasGeiping/breaching
Breaching privacy in federated learning scenarios for vision and text
zama-ai/concrete-ml
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on...
anupamkliv/FedERA
FedERA is a modular and fully customizable open-source FL framework, aiming to address these...
p2pfl/p2pfl
P2PFL is a decentralized federated learning library that enables federated learning on...