M
Michael Naehrig
Researcher at Microsoft
Publications - 98
Citations - 9234
Michael Naehrig is an academic researcher from Microsoft. The author has contributed to research in topics: Encryption & Homomorphic encryption. The author has an hindex of 38, co-authored 96 publications receiving 7912 citations. Previous affiliations of Michael Naehrig include Eindhoven University of Technology & University of Bristol.
Papers
More filters
Proceedings Article
CryptoNets: applying neural networks to encrypted data with high throughput and accuracy
TL;DR: It is shown that the cloud service is capable of applying the neural network to the encrypted data to make encrypted predictions, and also return them in encrypted form, which allows high throughput, accurate, and private predictions.
Proceedings ArticleDOI
Can homomorphic encryption be practical
TL;DR: A proof-of-concept implementation of the recent somewhat homomorphic encryption scheme of Brakerski and Vaikuntanathan, whose security relies on the "ring learning with errors" (Ring LWE) problem, and a number of application-specific optimizations to the encryption scheme, including the ability to convert between different message encodings in a ciphertext.
Book ChapterDOI
Pairing-Friendly elliptic curves of prime order
TL;DR: This paper describes a method to construct elliptic curves of prime order and embedding degree k = 12 and shows that the ability to handle log(D)/log(r) ~ (q–3)/(q–1) enables building curves with ρ ~ q/(q-1).
Journal Article
Pairing-friendly elliptic curves of prime order
TL;DR: In particular, for embedding degree k = 2q where q is prime, the authors showed that the ability to handle log(D)/log(r) ∼ (q - 3)/(q - 1) enables building elliptic curves with p ∼ q/(q- 1).
Book ChapterDOI
ML confidential: machine learning on encrypted data
TL;DR: A new class of machine learning algorithms in which the algorithm's predictions can be expressed as polynomials of bounded degree, and confidential algorithms for binary classification based on polynomial approximations to least-squares solutions obtained by a small number of gradient descent steps are proposed.