Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimation

no code implementations • 4 Jun 2021 • Nuttapong Attrapadung, Koki Hamada, Dai Ikarashi, Ryo Kikuchi, Takahiro Matsuda, Ibuki Mishina, Hiraku Morita, Jacob C. N. Schuldt

Our protocols are three-party protocols in the honest-majority setting, and we propose both passively secure and actively secure with abort variants.

Privacy Preserving

MOBIUS: Model-Oblivious Binarized Neural Networks

no code implementations • 29 Nov 2018 • Hiromasa Kitai, Jason Paul Cruz, Naoto Yanai, Naohisa Nishida, Tatsumi Oba, Yuji Unagami, Tadanori Teruya, Nuttapong Attrapadung, Takahiro Matsuda, Goichiro Hanaoka

A privacy-preserving framework in which a computational resource provider receives encrypted data from a client and returns prediction results without decrypting the data, i. e., oblivious neural network or encrypted prediction, has been studied in machine learning that provides prediction services.

BIG-bench Machine Learning Privacy Preserving