Timezone: »

 
Opacus: User-Friendly Differential Privacy Library in PyTorch
Ashkan Yousefpour · Igor Shilov · Alexandre Sablayrolles · Karthik Prasad · Mani Malek Esmaeili · John Nguyen · Sayan Ghosh · Akash Bharadwaj · Jessica Zhao · Graham Cormode · Ilya Mironov

@
in Privacy in Machine Learning (PriML) 2021 »
Event URL: https://openreview.net/forum?id=EopKEYBoI- »

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.

Author Information

Ashkan Yousefpour (Meta AI)
Igor Shilov (Meta AI)
Alexandre Sablayrolles (Meta AI)
Karthik Prasad (Facebook AI)
Mani Malek Esmaeili (Facebook)
John Nguyen (Facebook)
Sayan Ghosh (Facebook)
Akash Bharadwaj (Facebook)
Jessica Zhao (Facebook)
Graham Cormode (Meta AI)
Ilya Mironov (Meta (Responsible AI))

More from the Same Authors