arXiv 2104.123852021-04-27cs.LGcs.CR

Syft 0.5：一个可普遍部署的结构化透明平台

Syft 0.5: A Platform for Universally Deployable Structured Transparency

OpenMined；Edinburgh Napier University（爱丁堡龙比亚大学）；Memri；Politehnica University of Bucharest（布加勒斯特理工大学）；Philisense；École Supérieure en Informatique, Sidi Bel Abbès（西迪贝勒阿巴斯高等信息学院）；INRIA Paris（巴黎国家信息与自动化研究所）；ENS（巴黎高等师范学院）；PSL University（巴黎文理研究大学）；Arkhn；Tessella；University of Oxford（牛津大学）

Adam James Hall, Madhava Jay, Tudor Cebere, Bogdan Cebere, Koen Lennart van der Veen, George Muraru, Tongye Xu, Patrick Cason, William Abramson, Ayoub Benaissa,… 展开作者

Adam James Hall, Madhava Jay, Tudor Cebere, Bogdan Cebere, Koen Lennart van der Veen, George Muraru, Tongye Xu, Patrick Cason, William Abramson, Ayoub Benaissa, Chinmay Shah, Alan Aboudib, Théo Ryffel, Kritika Prakash, Tom Titcombe, Varun Kumar Khare, Maddie Shang, Ionesio Junior, Animesh Gupta, Jason Paumier, Nahua Kang, Vova Manannikov, Andrew Trask

备注：: ICLR 2021 Workshop on Distributed and Private Machine Learning (DPML 2021)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

我们提出了Syft 0.5，一个通用框架，结合了一组核心的隐私增强技术，促进了一套通用的结构化透明度系统。通过设计和实现一种新的隐私保护推理信息流，我们通过一个分裂的神经网络推理同态加密的激活信号，证明了这个框架。我们表明，进一步分裂模型的计算链显着减少了推理的计算时间和有效载荷大小的激活信号的模型保密的成本。我们评估我们提出的流程，就其提供的核心结构透明度原则。

英文摘要：

We present Syft 0.5, a general-purpose framework that combines a core group of privacy-enhancing technologies that facilitate a universal set of structured transparency systems. This framework is demonstrated through the design and implementation of a novel privacy-preserving inference information flow where we pass homomorphically encrypted activation signals through a split neural network for inference. We show that splitting the model further up the computation chain significantly reduces the computation time of inference and the payload size of activation signals at the cost of model secrecy. We evaluate our proposed flow with respect to its provision of the core structural transparency principles.

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。