TensorFHE plus : Fully Homomorphic Encryption Acceleration Based on Linear Algebra

doi:10.1109/TC.2025.3629614

CSpace

	TensorFHE plus : Fully Homomorphic Encryption Acceleration Based on Linear Algebra
	Sun, Yintai 1; Fan, Shengyu 2; Yin, Zhenhua 3; Song, Xinkai 4; Hu, Xing 4; Du, Zidong 4; Guo, Qi 4; Xu, Weizhi 5; Hou, Rui 2; Meng, Dan 2; Bian, Song 1; Zhang, Mingzhe 2
	2026-02-01
发表期刊	IEEE TRANSACTIONS ON COMPUTERS
ISSN	0018-9340
卷号	75 期号:2 页码:612-627
摘要	Fully Homomorphic Encryption (FHE) enables encrypted data processing on untrusted cloud servers, crucial for privacy-sensitive applications. Despite its potential, performance overheads (about $10,000\times$10,000x slower) limit adoption. ASIC accelerators outperform GPUs/FPGAs by optimizing specific operations but rely on costly 7nm processes and large on-chip memory, hindering cost-effective deployment. Balancing efficiency with manufacturing constraints remains critical. This paper presents TensorFHE+, a GPU-optimized FHE acceleration framework leveraging Tensor Cores to accelerate Number Theoretic Transform (NTT) operations. Key innovations include: 1) Decomposing CKKS kernels into vector/matrix operations for hardware utilization; 2) Vectorized modulo arithmetic; 3) Data layout optimization for memory efficiency. Evaluated on NVIDIA A100, TensorFHE+ outperforms TensorFHE[1] by 1.44 x in average (up to 1.69x on ResNet-20) and surpasses prior GPU implementations [2], [3]. The design also demonstrates compatibility with commercial linear algebra accelerators, enabling efficient FHE deployment.
关键词	Polynomials Kernel Optimization Vectors Transforms System-on-chip Symbols Servers Pipelines Linear accelerators FHE GPGPU HPC linear algebra modulo data layout
DOI	10.1109/TC.2025.3629614
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic
WOS记录号	WOS:001662961200003
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42874
专题	中国科学院计算技术研究所
通讯作者	Zhang, Mingzhe
作者单位	1.Beihang Univ, Sch Cyber Sci & Technol, Beijing 100191, Peoples R China 2.Inst Informat Engn, State Key Lab Informat Secur, CAS, Beijing 100085, Peoples R China 3.Cambricon Technol, Beijing 100101, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 5.Shandong Normal Univ, Sch Informat Sci & Engn, Jinan 250014, Peoples R China
推荐引用方式 GB/T 7714	Sun, Yintai,Fan, Shengyu,Yin, Zhenhua,et al. TensorFHE plus : Fully Homomorphic Encryption Acceleration Based on Linear Algebra[J]. IEEE TRANSACTIONS ON COMPUTERS,2026,75(2):612-627.
APA	Sun, Yintai.,Fan, Shengyu.,Yin, Zhenhua.,Song, Xinkai.,Hu, Xing.,...&Zhang, Mingzhe.(2026).TensorFHE plus : Fully Homomorphic Encryption Acceleration Based on Linear Algebra.IEEE TRANSACTIONS ON COMPUTERS,75(2),612-627.
MLA	Sun, Yintai,et al."TensorFHE plus : Fully Homomorphic Encryption Acceleration Based on Linear Algebra".IEEE TRANSACTIONS ON COMPUTERS 75.2(2026):612-627.