IACR News item: 15 September 2022
Ali Şah Özcan
ePrint Report
Homomorphic encryption (HE) is a cryptosystem that allows secure processing of encrypted data. One of the most popular HE schemes is the Brakerski-Fan-Vercauteren (BFV), which supports somewhat (SWHE) and fully homomorphic encryption (FHE). Since overly involved arithmetic operations of HE schemes are amenable to concurrent computation, GPU devices can be instrumental in facilitating the practical use of HE in real world applications thanks to their superior parallel processing capacity.
This paper presents an optimized and highly parallelized GPU library to accelerate the BFV scheme. This library includes state-of-the-art implementations of Number Theoretic Transform (NTT) and inverse NTT that minimize the GPU kernel function calls. It makes an efficient use of the GPU memory hierarchy and computes 128 NTT operations for ring dimension of $2^{14}$ only in $176.1~\mu s$ on RTX~3060Ti GPU. To the best of our knowlede, this is the fastest implementation in the literature. The library also improves the performance of the homomorphic operations of the BFV scheme. Although the library can be independently used, it is also fully integrated with the Microsoft SEAL library, which is a well-known HE library that also implements the BFV scheme. For one ciphertext multiplication, for the ring dimension $2^{14}$ and the modulus bit size of $438$, our GPU implementation offers $\mathbf{63.4}$ times speedup over the SEAL library running on a high-end CPU. The library compares favorably with other state-of-the-art GPU implementations of NTT and the BFV operations. Finally, we implement a privacy-preserving application that classifies encrpyted genome data for tumor types and achieve speedups of $42.98$ and $5.7$ over a CPU implementations using single and 16 threads, respectively. Our results indicate that GPU implementations can facilitate the deployment of homomorphic cryptographic libraries in real world privacy preserving applications.
This paper presents an optimized and highly parallelized GPU library to accelerate the BFV scheme. This library includes state-of-the-art implementations of Number Theoretic Transform (NTT) and inverse NTT that minimize the GPU kernel function calls. It makes an efficient use of the GPU memory hierarchy and computes 128 NTT operations for ring dimension of $2^{14}$ only in $176.1~\mu s$ on RTX~3060Ti GPU. To the best of our knowlede, this is the fastest implementation in the literature. The library also improves the performance of the homomorphic operations of the BFV scheme. Although the library can be independently used, it is also fully integrated with the Microsoft SEAL library, which is a well-known HE library that also implements the BFV scheme. For one ciphertext multiplication, for the ring dimension $2^{14}$ and the modulus bit size of $438$, our GPU implementation offers $\mathbf{63.4}$ times speedup over the SEAL library running on a high-end CPU. The library compares favorably with other state-of-the-art GPU implementations of NTT and the BFV operations. Finally, we implement a privacy-preserving application that classifies encrpyted genome data for tumor types and achieve speedups of $42.98$ and $5.7$ over a CPU implementations using single and 16 threads, respectively. Our results indicate that GPU implementations can facilitate the deployment of homomorphic cryptographic libraries in real world privacy preserving applications.
Additional news items may be found on the IACR news page.