Opacus: User-Friendly Differential Privacy Library in PyTorch

Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, Graham Cormode, Ilya Mironov

Keywords: Privacy, DP-SGD, Privacy-Preserving Machine Learning, PyTorch

TL;DR: We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy

Abstract: We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at https://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.

Paper Under Submission: The paper is NOT under submission at NeurIPS

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/opacus-user-friendly-differential-privacy/code)