arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.12840cs.LGcs.CRstat.ML
收藏

SEALion:加密数据神经网络推理框架

SEALion: a Framework for Neural Network Inference on Encrypted Data

University of Amsterdam(阿姆斯特丹大学);Deeptrace;CSIRO Data61(联邦科学与工业研究组织Data61)

Tim van Elsloo, Giorgio Patrini, Hamish Ivey-Law

摘要:

我们提出了SEALion:一个可扩展的框架,隐私保护机器学习与同态加密。它允许人们学习深度神经网络,可以无缝地用于加密数据的预测。该框架由两层组成:第一层基于TensorFlow和SEAL构建,并公开了标准代数和深度学习原语;第二层实现了类似Keras的语法,用于使用神经网络进行训练和推理。给定所需的安全级别,用户可以从编码和加密方案的细节中抽象出来,从而允许快速原型化。我们提出了两个应用程序,举例说明了我们的建议,这也是独立的利益的可扩展性:i)提高效率的神经网络推理的活动稀疏和ii)通过查询服务器端的变分自编码器,可以处理加密数据的迁移学习。

英文摘要:

We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework consists of two layers: the first is built upon TensorFlow and SEAL and exposes standard algebra and deep learning primitives; the second implements a Keras-like syntax for training and inference with neural networks. Given a required level of security, a user is abstracted from the details of the encoding and the encryption scheme, allowing quick prototyping. We present two applications that exemplifying the extensibility of our proposal, which are also of independent interest: i) improving efficiency of neural network inference by an activity sparsifier and ii) transfer learning by querying a server-side Variational AutoEncoder that can handle encrypted data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑