Efficiency optimization techniques in privacy-preserving federated learning with homomorphic encryption: A brief survey

Q Xie, S Jiang, L Jiang, Y Huang, Z Zhao… - IEEE Internet of …, 2024 - ieeexplore.ieee.org
Federated learning (FL) offers distributed machine learning on edge devices. However, the
FL model raises privacy concerns. Various techniques, such as homomorphic encryption …

Homomorphic encryption for machine learning in medicine and bioinformatics

A Wood, K Najarian, D Kahrobaei - ACM Computing Surveys (CSUR), 2020 - dl.acm.org
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 …

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 …

A full RNS variant of approximate homomorphic encryption

JH Cheon, K Han, A Kim, M Kim, Y Song - Selected Areas in Cryptography …, 2019 - Springer
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 …

HEAX: An architecture for computing on encrypted data

MS Riazi, K Laine, B Pelton, W Dai - Proceedings of the twenty-fifth …, 2020 - dl.acm.org
With the rapid increase in cloud computing, concerns surrounding data privacy, security, and
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

H Chen, W Dai, M Kim, Y Song - Proceedings of the 2019 ACM SIGSAC …, 2019 - dl.acm.org
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 …

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 …

Labeled PSI from fully homomorphic encryption with malicious security

H Chen, Z Huang, K Laine, P Rindal - Proceedings of the 2018 ACM …, 2018 - dl.acm.org
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 …

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 …

Improved bootstrapping for approximate homomorphic encryption

H Chen, I Chillotti, Y Song - Annual International Conference on the Theory …, 2019 - Springer
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 …