TY - JOUR
T1 - Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities
AU - Pulido-Gaytan, Bernardo
AU - Tchernykh, Andrei
AU - Cortés-Mendoza, Jorge M.
AU - Babenko, Mikhail
AU - Radchenko, Gleb
AU - Avetisyan, Arutyun
AU - Drozdov, Alexander Yu
N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.
PY - 2021/3/8
Y1 - 2021/3/8
N2 - Classical machine learning modeling demands considerable computing power for internal calculations and training with big data in a reasonable amount of time. In recent years, clouds provide services to facilitate this process, but it introduces new security threats of data breaches. Modern encryption techniques ensure security and are considered as the best option to protect stored data and data in transit from an unauthorized third-party. However, a decryption process is necessary when the data must be processed or analyzed, falling into the initial problem of data vulnerability. Fully Homomorphic Encryption (FHE) is considered the holy grail of cryptography. It allows a non-trustworthy third-party resource to process encrypted information without disclosing confidential data. In this paper, we analyze the fundamental concepts of FHE, practical implementations, state-of-the-art approaches, limitations, advantages, disadvantages, potential applications, and development tools focusing on neural networks. In recent years, FHE development demonstrates remarkable progress. However, current literature in the homomorphic neural networks is almost exclusively addressed by practitioners looking for suitable implementations. It still lacks comprehensive and more thorough reviews. We focus on the privacy-preserving homomorphic encryption cryptosystems targeted at neural networks identifying current solutions, open issues, challenges, opportunities, and potential research directions.
AB - Classical machine learning modeling demands considerable computing power for internal calculations and training with big data in a reasonable amount of time. In recent years, clouds provide services to facilitate this process, but it introduces new security threats of data breaches. Modern encryption techniques ensure security and are considered as the best option to protect stored data and data in transit from an unauthorized third-party. However, a decryption process is necessary when the data must be processed or analyzed, falling into the initial problem of data vulnerability. Fully Homomorphic Encryption (FHE) is considered the holy grail of cryptography. It allows a non-trustworthy third-party resource to process encrypted information without disclosing confidential data. In this paper, we analyze the fundamental concepts of FHE, practical implementations, state-of-the-art approaches, limitations, advantages, disadvantages, potential applications, and development tools focusing on neural networks. In recent years, FHE development demonstrates remarkable progress. However, current literature in the homomorphic neural networks is almost exclusively addressed by practitioners looking for suitable implementations. It still lacks comprehensive and more thorough reviews. We focus on the privacy-preserving homomorphic encryption cryptosystems targeted at neural networks identifying current solutions, open issues, challenges, opportunities, and potential research directions.
KW - Cloud security
KW - Homomorphic encryption
KW - Machine learning
KW - Neural networks
KW - Privacy-preserving
UR - https://doi.org/10.1007/s12083-021-01076-8
U2 - 10.1007/s12083-021-01076-8
DO - 10.1007/s12083-021-01076-8
M3 - Article
VL - 14
SP - 1666
EP - 1691
JO - Peer-to-Peer Networking and Applications
JF - Peer-to-Peer Networking and Applications
IS - 3
M1 - 3
ER -