Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

PhantomFHE: A CUDA-Accelerated Homomorphic Encryption Library

Privacy Preserving Convolutional Neural Network using Homomorphic Encryption for secure inference

R package that provides estimation methods for Gravity Models

Stay updated with the latest deadlines for top Multi-Party Computation (MPC) events, including conferences, journals, and workshops. Never miss an important submission again!

Curl: Private LLMs through Wavelet-Encoded Look-Up Tables

A compiled list of resources and materials for PPML

Samples of multi-class text classification with Differential Privacy Tensorflow 2.0

Sisyphus: A Cautionary Tale of Using Polynomial Activations in Privacy-Preserving Deep Learning

A capstone project in collaboration with Zama to develop a privacy-preserving machine learning model using PPML, FHE and Concrete ML to detect banking frauds.

Hands-on part of the Federated Learning and Privacy-Preserving ML tutorial given at VISUM 2022

Extension of the MOTION2NX framework to implement neural network inferencing task where the data is supplied to the “secure compute servers” by the “data providers”.

End-to-End Python econometric pipeline for modeling geopolitical risk in international trade using advanced Bayesian filtering, high-dimensional fixed effects, and split-panel jackknife inference. Replicates Hardwick's (2025) methodology with full robustness testing and automated reporting.

Repo for Mphasis PPML Research Project

Companion repo to "SoK: Connecting the Dots in Privacy-Preserving ML — Systematization of MPC Protocols and Conversions Between Secret Sharing Schemes." Actively maintained to track new MPC protocols and secret-sharing conversions as the field evolves post-publication.

🌍 Model political distance and trade dynamics using a quantitative framework to enhance understanding of international trade relationships.

Privacy-preserving Machine Learning for image classification using three datasets: MNIST, FashionMNIST, and CIFAR10

A Learning Journal on (Privacy-Preserving) AI for Medicine and Healthcare

Learn how to apply core privacy principles and techniques to the data science and machine learning workflows with Python open source libraries for privacy-preserving machine learning.

A C++ framework for privacy-preserving machine learning using HE and TEE. Prototype of deploying homomorphic encryption library (HElib) in a TEE (Microsoft OpenEnclave)