Efficiency optimization techniques in privacy-preserving federated learning with homomorphic encryption: A brief survey
Federated learning (FL) offers distributed machine learning on edge devices. However, the
FL model raises privacy concerns. Various techniques, such as homomorphic encryption …
FL model raises privacy concerns. Various techniques, such as homomorphic encryption …
Homomorphic encryption for machine learning in medicine and bioinformatics
Machine learning and statistical techniques are powerful tools for analyzing large amounts
of medical and genomic data. On the other hand, ethical concerns and privacy regulations …
of medical and genomic data. On the other hand, ethical concerns and privacy regulations …
POSEIDON: Privacy-preserving federated neural network learning
S Sav, A Pyrgelis, JR Troncoso-Pastoriza… - arXiv preprint arXiv …, 2020 - arxiv.org
In this paper, we address the problem of privacy-preserving training and evaluation of neural
networks in an $ N $-party, federated learning setting. We propose a novel system …
networks in an $ N $-party, federated learning setting. We propose a novel system …
A full RNS variant of approximate homomorphic encryption
Abstract The technology of Homomorphic Encryption (HE) has improved rapidly in a few
years. The newest HE libraries are efficient enough to use in practical applications. For …
years. The newest HE libraries are efficient enough to use in practical applications. For …
HEAX: An architecture for computing on encrypted data
With the rapid increase in cloud computing, concerns surrounding data privacy, security, and
confidentiality also have been increased significantly. Not only cloud providers are …
confidentiality also have been increased significantly. Not only cloud providers are …
Efficient multi-key homomorphic encryption with packed ciphertexts with application to oblivious neural network inference
Homomorphic Encryption (HE) is a cryptosystem which supports computation on encrypted
data. Ló pez-Alt et al.(STOC 2012) proposed a generalized notion of HE, called Multi-Key …
data. Ló pez-Alt et al.(STOC 2012) proposed a generalized notion of HE, called Multi-Key …
Towards deep neural network training on encrypted data
K Nandakumar, N Ratha… - Proceedings of the …, 2019 - openaccess.thecvf.com
While deep learning is a valuable tool for solving many tough problems in computer vision,
the success of deep learning models is typically determined by:(i) availability of sufficient …
the success of deep learning models is typically determined by:(i) availability of sufficient …
Labeled PSI from fully homomorphic encryption with malicious security
Private Set Intersection (PSI) allows two parties, the sender and the receiver, to compute the
intersection of their private sets without revealing extra information to each other. We are …
intersection of their private sets without revealing extra information to each other. We are …
Better bootstrapping for approximate homomorphic encryption
K Han, D Ki - Cryptographers' Track at the RSA Conference, 2020 - Springer
Abstract After Cheon et al.(Asiacrypt'17) proposed an approximate homomorphic encryption
scheme, HEAAN, for operations between encrypted real (or complex) numbers, the scheme …
scheme, HEAAN, for operations between encrypted real (or complex) numbers, the scheme …
Improved bootstrapping for approximate homomorphic encryption
Since Cheon et al. introduced a homomorphic encryption scheme for approximate arithmetic
(Asiacrypt'17), it has been recognized as suitable for important real-life usecases of …
(Asiacrypt'17), it has been recognized as suitable for important real-life usecases of …