Haoran Zhu, Pavankumar Murali, et al.
NeurIPS 2020
Homomorphic Encryption (HE) is a cryptographic tool that allows performing computation under encryption, which is used by many privacy-preserving machine learning solutions, for example, to perform secure classification. Modern deep learning applications yield good performance for example in image processing tasks benchmarks by including many skip connections. The latter appears to be very costly when attempting to execute model inference under HE. In this paper, we show that by replacing (mid-term) skip connections with (short-term) Dirac parameterization and (long-term) shared-source skip connection we were able to reduce the skip connections burden for HE-based solutions, achieving computing power improvement for the same accuracy.
Haoran Zhu, Pavankumar Murali, et al.
NeurIPS 2020
Gosia Lazuka, Andreea Simona Anghel, et al.
SC 2024
Ehud Aharoni, Nir Drucker, et al.
CSCML 2023
Fearghal O'Donncha, Malvern Madondo, et al.
AGU Fall 2022