Opacus: User-Friendly Differential Privacy Library in PyTorch

• DOI: 10.48550/arxiv.2109.12298
• Publication Date: 2021-01-01
• Authors: Yousefpour, Ashkan; Shilov, Igor; Sablayrolles, Ale...; Testuggine, Davide; Prasad, Karthik; Malek, Mani; Nguyen, John; Ghosh, Sayan; Bharadwaj, Akash; Zhao, Jessica; Cormode, Graham; Mironov, Ilya
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Cryptography and Security; 01 natural sciences; Cryptography and Security (cs.CR); 0105 earth and related environmental sciences; Machine Learning (cs.LG)

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, GRU (and generic RNN), and embedding, right out of the box and provides the means for supporting other user-defined layers. Opacus computes batched per-sample gradients, providing higher 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 benchmark it against other frameworks for training models with differential privacy as well as standard PyTorch.<br/>Privacy in Machine Learning (PriML) workshop, NeurIPS 2021<br/>