TY - GEN
T1 - A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption
AU - Pulido-Gaytan, L.B.
AU - Tchernykh, A.
AU - Cortés-Mendoza, J.M.
AU - Babenko, M.
AU - State, South
N1 - Conference code: 255329
Export Date: 27 August 2021
Correspondence Address: Tchernykh, A.; CICESE Research Center, carr. Tijuana-Ensenada 3918, Mexico; email: chernykh@cicese.edu.mx
Funding details: Ministry of Education and Science of the Russian Federation, Minobrnauka, 075-15-2020-788
Funding text 1: Acknowledgment. This work was partially supported by the Ministry of Education and Science of Russian Federation (Project 075-15-2020-788).
PY - 2021
Y1 - 2021
N2 - The secure and efficient processing of private information in the cloud computing paradigm is still an open issue. New security threats arise with the increasing volume of data into cloud storage, where cloud providers require high levels of trust, and data breaches are significant problems. Encrypting the data with conventional schemes is considered the best option to avoid security problems. However, a decryption process is necessary when the data must be processed, but it falls into the initial problem of data vulnerability. The user cannot operate on the data directly and must download it to perform the computations locally. In this context, Fully Homomorphic Encryption (FHE) is considered the holy grail of cryptography in order to solve cybersecurity problems, it allows a non-trustworthy third-party resource to blindly process encrypted information without disclosing confidential data. FHE is a valuable capability in a world of distributed computation and heterogeneous networking. In this survey, we present a comprehensive review of theoretical concepts, state-of-the-art, limitations, potential applications, and development tools in the domain of FHE. Moreover, we show the intersection of FHE and machine learning from a theoretical and a practical point of view and identify potential research directions to enrich Machine Learning as a Service, a new paradigm of cloud computing. Specifically, this paper aims to be a guide to researchers and practitioners interested in learning, applying, and extending knowledge in FHE over machine learning. © 2021, Springer Nature Switzerland AG.
AB - The secure and efficient processing of private information in the cloud computing paradigm is still an open issue. New security threats arise with the increasing volume of data into cloud storage, where cloud providers require high levels of trust, and data breaches are significant problems. Encrypting the data with conventional schemes is considered the best option to avoid security problems. However, a decryption process is necessary when the data must be processed, but it falls into the initial problem of data vulnerability. The user cannot operate on the data directly and must download it to perform the computations locally. In this context, Fully Homomorphic Encryption (FHE) is considered the holy grail of cryptography in order to solve cybersecurity problems, it allows a non-trustworthy third-party resource to blindly process encrypted information without disclosing confidential data. FHE is a valuable capability in a world of distributed computation and heterogeneous networking. In this survey, we present a comprehensive review of theoretical concepts, state-of-the-art, limitations, potential applications, and development tools in the domain of FHE. Moreover, we show the intersection of FHE and machine learning from a theoretical and a practical point of view and identify potential research directions to enrich Machine Learning as a Service, a new paradigm of cloud computing. Specifically, this paper aims to be a guide to researchers and practitioners interested in learning, applying, and extending knowledge in FHE over machine learning. © 2021, Springer Nature Switzerland AG.
KW - Cloud security
KW - Fully homomorphic encryption
KW - Machine learning as a service
KW - Cloud computing
KW - Digital storage
KW - Machine learning
KW - Privacy by design
KW - Surveys
KW - Trusted computing
KW - Conventional schemes
KW - Distributed computations
KW - Encrypted informations
KW - Heterogeneous networking
KW - Potential researches
KW - Privacy preserving
KW - Private information
KW - Cryptography
U2 - 10.1007/978-3-030-68035-0_9
DO - 10.1007/978-3-030-68035-0_9
M3 - Conference Paper
SN - 18650929 (ISSN); 9783030680343 (ISBN)
VL - 1327
SP - 115
EP - 129
BT - Latin American High Performance Computing Conference
T2 - 7th Latin American High Performance Computing Conference
Y2 - 2 September 2020 through 4 September 2020
ER -