Differential Privacy Python Packages

interpret-core

Fit interpretable models. Explain blackbox machine learning.

interpret

Fit interpretable models. Explain blackbox machine learning.

opacus

Training PyTorch models with differential privacy

dp-accounting

Google's differential privacy libraries.

opendp

The core library of differential privacy algorithms powering the OpenDP Project.

riskcal

Measure and calibrate operational privacy risks for differentially private algorithms.

smartnoise-sql

Tools and service for differentially private processing of tabular and relational data

diffprivlib

Diffprivlib: The IBM Differential Privacy Library

mostlyai

Synthetic Data SDK ✨

tmlt-core

Tumult Core is a collection of composable components for implementing algorithms to perform differentially private computations.

python-dp

The Python Differential Privacy Library. Built on top of: https://github.com/google/differential-privacy

mostlyai-engine

Synthetic Data Engine 💎

secretflow

A unified framework for privacy-preserving data analysis and machine learning

gretel-synthetics

Synthetic data generators for structured and unstructured text, featuring differentially private learning.

smartnoise-synth

Tools and service for differentially private processing of tabular and relational data

secretflow-lite

A unified framework for privacy-preserving data analysis and machine learning

synthpriv

Tabular data synthesis preserving differential privacy (DP-SGAN, DP copula, ECDF marginals)

sacroml

Collection of tools and resources for managing the statistical disclosure control of trained machine learning models

diffpriv

A python package for differential privacy and encryption.

opendp-smartnoise-core

Python language bindings for smartnoise-core.

tmlt-analytics

Tumult Analytics is a Python library for privately computing aggregate queries on tabular data. It is built atop the Tumult Core library.

pfl

Simulation framework for accelerating research in Private Federated Learning

dp-sequential-events

Differential privacy for sequential event logs, anonymizing case IDs and timestamps while preserving statistical properties.

aisdc

Collection of tools and resources for managing the statistical disclosure control of trained machine learning models