Diffprivlib: The IBM Differential Privacy Library
Diffprivlib is a general-purpose library for experimenting with, investigating and developing applications in, differential privacy.
Main Characteristic
Use diffprivlib if you are looking to:
1/ Experiment with differential privacy
2/ Explore the impact of differential privacy on machine learning accuracy using classification and clustering models
3/ Build your own differential privacy applications, using our extensive collection of mechanisms
Technical Categories
Machine learning
Business Categories
Cloud, Edge and Infrastructure
Last updated
16.01.2023 - 15:54
Detailed Description
Diffprivlib is comprised of four major components:
- Mechanisms: These are the building blocks of differential privacy, and are used in all models that implement differential privacy. Mechanisms have little or no default settings, and are intended for use by experts implementing their own models. They can, however, be used outside models for separate investigations, etc.
- Models: This module includes machine learning models with differential privacy. Diffprivlib currently has models for clustering, classification, regression, dimensionality reduction and pre-processing.
- Tools: Diffprivlib comes with a number of generic tools for differentially private data analysis. This includes differentially private histograms, following the same format as Numpy's histogram function.
- Accountant: The BudgetAccountant class can be used to track privacy budget and calculate total privacy loss using advanced composition techniques.