1. Syft 0.5: A Platform for Universally Deployable Structured Transparency
- Author
-
Hall, Adam James, Jay, Madhava, Cebere, Tudor, Cebere, Bogdan, van der Veen, Koen Lennart, Muraru, George, Xu, Tongye, Cason, Patrick, Abramson, William, Benaissa, Ayoub, 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, and Trask, Andrew
- Subjects
Computer Science - Machine Learning ,Computer Science - Cryptography and Security - Abstract
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., Comment: ICLR 2021 Workshop on Distributed and Private Machine Learning (DPML 2021)
- Published
- 2021