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

opendp

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

dp-accounting

Google's differential privacy libraries.

diffprivlib

Diffprivlib: The IBM Differential Privacy Library

smartnoise-sql

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

mostlyai

Synthetic Data SDK ✨

mostlyai-engine

Synthetic Data Engine 💎

secretflow

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

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

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

dp-sequential-events

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

sdsa

Open-source, self-hosted data obfuscation and policy-based sanitization for tabular datasets, with privacy reports

tmlt-analytics

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

secretflow-lite

SecretFlow Lite

riskcal

Compute f-DP trade-off curves and calibrate differentially private algorithms to operational privacy risk measures

synthhub

One unified API for differentially private synthetic data

trasgodp

Local differential privacy mechanisms

aisdc

Tools for the statistical disclosure control of machine learning models

diffpriv

A Differential Privacy Package

dpmm

dpmm: a library for synthetic tabular data generation with rich functionality and end-to-end Differential Privacy guarantees