Paper 2025/124

GPU Implementations of Three Different Key-Switching Methods for Homomorphic Encryption Schemes

Ali Şah Özcan, Sabanci University
Erkay Savaş, Sabanci University
Abstract

In this work, we report on the latest GPU implementations of the three well-known methods for the key switching operation, which is critical for Fully Homomorphic Encryption (FHE). Additionally, for the first time in the literature, we provide implementations of all three methods in GPU for leveled CKKS schemes. To ensure a fair comparison, we employ the most recent GPU implementation of the number-theoretic transform (NTT), which is the most time-consuming operation in key switching, and evaluate the performance across two fully homomorphic schemes: BFV and CKKS. Furthermore, we highlight the advantages and shortcomings of the three methods in the context of leveled HE schemes, and discuss other aspects such as memory requirements. Our GPU implementation is integrated with HEonGPU Library and delivers up to a ×380 improvement in execution time compared to the Microsoft SEAL Library. Since key switching is a specialized form of the external product common in many HE schemes, our results are directly relevant to time-intensive homomorphic operations such as relinearization and rotation. As homomorphic rotation is one of the most dominant operations in bootstrapping, our results are also applicable in bootstrapping algorithms of BFV, BGV and CKKS schemes.

Metadata
Available format(s)
PDF
Category
Implementation
Publication info
Preprint.
Keywords
GPUFully Homomorphic EncryptionHardware AccelerationBFVCKKSKey-SwitchingHybrid Homomorphic Encryption
Contact author(s)
alisah @ sabanciuniv edu
erkays @ sabanciuniv edu
History
2025-01-27: approved
2025-01-26: received
See all versions
Short URL
https://ia.cr/2025/124
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2025/124,
      author = {Ali Şah Özcan and Erkay Savaş},
      title = {{GPU} Implementations of Three Different Key-Switching Methods for Homomorphic Encryption Schemes},
      howpublished = {Cryptology {ePrint} Archive, Paper 2025/124},
      year = {2025},
      url = {https://eprint.iacr.org/2025/124}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.