Results 31 to 40 of about 5,430 (195)

SecureBP from Homomorphic Encryption

Security and Communication Networks, Volume 2020, Issue 1, 2020., 2020
We present a secure backpropagation neural network training model (SecureBP), which allows a neural network to be trained while retaining the confidentiality of the training data, based on the homomorphic encryption scheme. We make two contributions.
Qinju Liu, Xianhui Lu, Fucai Luo, Shuai Zhou, Jingnan He, Kunpeng Wang, Stelvio Cimato   +6 more
wiley   +1 more source

Privacy-Preserving Feature Selection with Fully Homomorphic Encryption

Algorithms, 2022
For the feature selection problem, we propose an efficient privacy-preserving algorithm. Let D, F, and C be data, feature, and class sets, respectively, where the feature value x(Fi) and the class label x(C) are given for each x∈D and Fi∈F. For a triple (
Shinji Ono, Jun Takata, Masaharu Kataoka, Tomohiro I, Kilho Shin, Hiroshi Sakamoto   +5 more
doaj   +1 more source

Theoretical and Experimental Investigations of a Passively Mode-Locked Nd" Glass Laser [PDF]

, 1981
The presented theoretical model for a mode-locked Nd-glass laser simultaneously takes into account dynamics of the mode-locking dye, amplification saturation and radiation background.
Kolmeder, Christian, Zinth, Wolfgang
core   +1 more source

Building Blocks for LSTM Homomorphic Evaluation with TFHE

, 2023
Long Short-Term Memory (LSTM) is a Neural Network (NN) type that creates temporal connections between its nodes. It models sequence data for applications such as speech recognition, image captioning, DNA sequence analysis, and sentence translation. Applications that are often subject to privacy constraints.
Trama, Daphne, Clet, Pierre-Emmanuel, Boudguiga, Aymen, Sirdey, Renaud   +3 more
openaire   +2 more sources

YATA: Yet Another TFHE Accelerator with Key Compression and Radix-8 NTT

Transactions on Cryptographic Hardware and Embedded Systems
This paper introduces a silicon-proven ASIC accelerator, YATA, specifically designed for TFHE’s most demanding operation, the BlindRotate. The architecture tackles the main bottleneck in TFHE—massive memory bandwidth—by applying Key Compression to ...
Kotaro Matsuoka, Takashi Sato
doaj   +1 more source

SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Search [PDF]

, 2020
The $k$-Nearest Neighbor Search ($k$-NNS) is the backbone of several cloud-based services such as recommender systems, face recognition, and database search on text and images.
Chen, Hao, Chillotti, Ilaria, Dong, Yihe, Poburinnaya, Oxana, Razenshteyn, Ilya, Riazi, M. Sadegh   +5 more
core   +1 more source

A Survey on Homomorphic Encryption Schemes: Theory and Implementation

, 2017
Legacy encryption systems depend on sharing a key (public or private) among the peers involved in exchanging an encrypted message. However, this approach poses privacy concerns.
Acar, Abbas, Aksu, Hidayet, Conti, Mauro, Uluagac, A. Selcuk   +3 more
core   +1 more source

Multi-Key Homomorphic Encryption from TFHE

, 2019
In this paper, we propose a Multi-Key Homomorphic Encryption (MKHE) scheme by generalizing the low-latency homomorphic encryption by Chillotti et al. (ASIACRYPT 2016). Our scheme can evaluate a binary gate on ciphertexts encrypted under different keys followed by a bootstrapping.
Hao Chen, Ilaria Chillotti, Yongsoo Song
openaire   +2 more sources

Hitchhiker's Guide to the TFHE Scheme

, 2023
Abstract Also referred to as the holy grail of cryptography, Fully Homomorphic Encryption (FHE) allows for arbitrary calculations over encrypted data. First proposed as a challenge by Rivest et al.
openaire   +1 more source

Multi-Key Homomorphic Encryption Scheme with Multi-Output Programmable Bootstrapping

Mathematics, 2023
Multi-key Homomorphic Encryption (MKHE) scheme can homomorphically evaluate ciphertexts encrypted by different keys, which can effectively protect the privacy information of data holders in the joint computing of cloud services.
Lingwu Li, Ruwei Huang
doaj   +1 more source