Opacus: User-Friendly Differential Privacy Library in PyTorch

09/25/2021
by   Ashkan Yousefpour, et al.
0

We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus.ai). Opacus is designed for simplicity, flexibility, and speed. It provides a simple and user-friendly API, and enables machine learning practitioners to make a training pipeline private by adding as little as two lines to their code. It supports a wide variety of layers, including multi-head attention, convolution, LSTM, and embedding, right out of the box, and it also provides the means for supporting other user-defined layers. Opacus computes batched per-sample gradients, providing better efficiency compared to the traditional "micro batch" approach. In this paper we present Opacus, detail the principles that drove its implementation and unique features, and compare its performance against other frameworks for differential privacy in ML.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/04/2019

Diffprivlib: The IBM Differential Privacy Library

Since its conception in 2006, differential privacy has emerged as the de...
research
07/01/2016

Deep Learning with Differential Privacy

Machine learning techniques based on neural networks are achieving remar...
research
12/15/2018

A General Approach to Adding Differential Privacy to Iterative Training Procedures

In this work we address the practical challenges of training machine lea...
research
08/05/2020

More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence

Artificial Intelligence (AI) has attracted a great deal of attention in ...
research
05/25/2023

Private Meeting Summarization Without Performance Loss

Meeting summarization has an enormous business potential, but in additio...
research
09/22/2021

Do I Get the Privacy I Need? Benchmarking Utility in Differential Privacy Libraries

An increasing number of open-source libraries promise to bring different...
research
05/25/2015

Expresso : A user-friendly GUI for Designing, Training and Exploring Convolutional Neural Networks

With a view to provide a user-friendly interface for designing, training...

Please sign up or login with your details

Forgot password? Click here to reset