Enabling Homomorphically Encrypted Inference for Large DNN Models

no code implementations • 30 Mar 2021 • Guillermo Lloret-Talavera, Marc Jorda, Harald Servat, Fabian Boemer, Chetan Chauhan, Shigeki Tomishima, Nilesh N. Shah, Antonio J. Peña

The proliferation of machine learning services in the last few years has raised data privacy concerns.

Trustworthy AI Inference Systems: An Industry Research View

no code implementations • 10 Aug 2020 • Rosario Cammarota, Matthias Schunter, Anand Rajan, Fabian Boemer, Ágnes Kiss, Amos Treiber, Christian Weinert, Thomas Schneider, Emmanuel Stapf, Ahmad-Reza Sadeghi, Daniel Demmler, Joshua Stock, Huili Chen, Siam Umar Hussain, Sadegh Riazi, Farinaz Koushanfar, Saransh Gupta, Tajan Simunic Rosing, Kamalika Chaudhuri, Hamid Nejatollahi, Nikil Dutt, Mohsen Imani, Kim Laine, Anuj Dubey, Aydin Aysu, Fateme Sadat Hosseini, Chengmo Yang, Eric Wallace, Pamela Norton

Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time.

nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data

2 code implementations • 12 Aug 2019 • Fabian Boemer, Anamaria Costache, Rosario Cammarota, Casimir Wierzynski

The proposed framework leverages the CKKS scheme, whose support for real numbers is friendly to data science, and a client-aided model using a two-party approach to compute activation functions.

Cryptography and Security

nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

2 code implementations • 23 Oct 2018 • Fabian Boemer, Yixing Lao, Casimir Wierzynski

Homomorphic encryption (HE)--the ability to perform computations on encrypted data--is an attractive remedy to increasing concerns about data privacy in the field of machine learning.

Cryptography and Security