Cross-Platform Benchmarking of the FHE Libraries: Novel Insights into SEAL and Openfhe
Faneela, Jawad Ahmad, Baraq Ghaleb, Sana Ullah Jan, William J. Buchanan
TL;DR
The paper tackles the practical performance of fully homomorphic encryption by benchmarking SEAL and OpenFHE across the BGV and CKKS schemes on Linux and Windows. It systematically analyzes two core operations, addition and multiplication, under varying parameter settings, including polymodulus degree, ciphertext modulus, and scaling factors, to assess efficiency and memory usage. The results show OpenFHE generally outperforms SEAL, with Linux consistently providing the best performance, especially for CKKS, suggesting OpenFHE as the more scalable choice for real-world privacy-preserving applications. This work offers actionable guidance for researchers and practitioners in selecting FHE libraries and configurations and highlights avenues for further hardware-accelerated and scheme-diverse evaluations.
Abstract
The rapid growth of cloud computing and data-driven applications has amplified privacy concerns, driven by the increasing demand to process sensitive data securely. Homomorphic encryption (HE) has become a vital solution for addressing these concerns by enabling computations on encrypted data without revealing its contents. This paper provides a comprehensive evaluation of two leading HE libraries, SEAL and OpenFHE, examining their performance, usability, and support for prominent HE schemes such as BGV and CKKS. Our analysis highlights computational efficiency, memory usage, and scalability across Linux and Windows platforms, emphasizing their applicability in real-world scenarios. Results reveal that Linux outperforms Windows in computation efficiency, with OpenFHE emerging as the optimal choice across diverse cryptographic settings. This paper provides valuable insights for researchers and practitioners to advance privacy-preserving applications using FHE.