Managing Differential Privacy in Large-Scale Systems

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

Concrete: TFHE Compiler that converts python programs into FHE equivalent

Synthetic data generation for tabular data

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…

Code for hands-on experience with reconstruction attacks in a simple setting

DPLab: Benchmarking Differential Privacy Aggregation Operations

The Privacy Adversarial Framework (PAF) is a knowledge base of privacy-focused adversarial tactics and techniques. PAF is heavily inspired by MITRE ATT&CK®.

An Implementation of Incremental Distributed Point Functions in C++

Programming language for literate programming law specification

HedgeDoc - Ideas grow better together

Simplified Implementation of Facebook's TAO, but encrypted

Benchmark for differential privacy budget schedulers, based on an Alibaba cluster trace

This document describes the Distributed Aggregation Protocol (DAP) being developed by the PPM working group at IETF.

VDAF specification

Implementation of Prio in Rust.

Implementation of DAP

Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.

💻 Command-line tool for Home Assistant

A Go implementation of the protocols for {MPSI, MPSIU, MPSI-Sum, MPSIU-Sum} described in Estimating Incidental Collection in Foreign Intelligence Surveillance: Large-Scale Multiparty Private Set In…

High performance model preprocessing library on PyTorch

Dynamic DNS shell script for Gandi

An open-source time-series SQL database optimized for fast ingest and complex queries. Packaged as a PostgreSQL extension.