Syft 0.5: A Platform for Universally Deployable Structured Transparency

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 f...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Hall, Adam James, Madhava, Jay, Cebere, Tudor, Cebere, Bogdan, Koen Lennart van der Veen, Muraru, George, Xu, Tongye, Cason, Patrick, Abramson, William, Ayoub Benaissa, Shah, Chinmay, Aboudib, Alan, Ryffel, Théo, Prakash, Kritika, Titcombe, Tom, Khare, Varun Kumar, Shang, Maddie, Junior, Ionesio, Gupta, Animesh, Paumier, Jason, Kang, Nahua, Manannikov, Vova, Trask, Andrew
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 27.04.2021
Subjects
Chain scission
Computation
Encryption
Inference
Information flow
Neural networks
Privacy
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422