W
Wei Dai
Researcher at Microsoft
Publications - 23
Citations - 843
Wei Dai is an academic researcher from Microsoft. The author has contributed to research in topics: Homomorphic encryption & Encryption. The author has an hindex of 10, co-authored 23 publications receiving 374 citations. Previous affiliations of Wei Dai include Worcester Polytechnic Institute.
Papers
More filters
Proceedings ArticleDOI
Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference
TL;DR: This paper presents multi-key variants of two HE schemes with packed ciphertexts, and presents new relinearization algorithms which are simpler and faster than previous method by Chen et al. (TCC 2017).
Proceedings ArticleDOI
HEAX: An Architecture for Computing on Encrypted Data
TL;DR: In this paper, the authors present HEAX, a novel hardware architecture for FHE that achieves unprecedented performance improvements by leveraging multiple levels of parallelism, ranging from ciphertext-level to fine-grained modular arithmetic level.
Posted Content
HEAX: An Architecture for Computing on Encrypted Data
TL;DR: HEAX is presented, a novel hardware architecture for FHE that achieves unprecedented performance improvements and a new highly-parallelizable architecture for number-theoretic transform (NTT) which can be of independent interest as NTT is frequently used in many lattice-based cryptography systems.
Book ChapterDOI
cuHE: A Homomorphic Encryption Accelerator Library
Wei Dai,Berk Sunar +1 more
TL;DR: In this article, a CUDA GPU library is proposed to accelerate evaluations with homomorphic schemes defined over polynomial rings enabled with a number of optimizations including algebraic techniques for efficient evaluation, memory minimization techniques, memory and thread scheduling and low level CUDA hand-tuned assembly optimizations.
Proceedings ArticleDOI
Accelerating NTRU based homomorphic encryption using GPUs
Wei Dai,Yarkin Doröz,Berk Sunar +2 more
TL;DR: In this article, a large polynomial arithmetic library optimized for Nvidia GPUs was proposed to support fully homomorphic encryption schemes, and the library was used to evaluate homomorphic evaluation of two block ciphers: Prince and AES.