HEDWIG: Homomorphic Encryption Accelerator Design Using BFV-HPS With HiGh-Speed Fixed-Point Approximation


연구 분야: Cryptography



학회: FPGA '25: Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays


초록

Homomorphic encryption enables computations on the ciphertext to preserve data privacy with significant computational overhead compared to plaintext computations. In response to this challenge, we present HEDWIG, a novel end-to-end hardware acceleration system designed to enhance the efficiency of homomorphic encryption, specifically tailored for the latest BFV-HPS scheme. To the best of our knowledge, this is the first hardware accelerator for the BFV-HPS scheme variant. Key contributions include computation workload reduction via approximation, hardware resource optimization on modular computation modules, and computation workflow optimization to improve HE algorithm efficiency. The proposed HEDWIG is employed to perform homomorphic evaluations over machine learning model inference with a high reduction in DSP usage compared to prior BFV RNS variants FPGA accelerator with clock frequency reached 300MHz.


Author Profile
Antian Wang

Purdue University Fort Wayne Fort Wayne Indiana USA

United States
Author Profile
Weihang Tan

ScaleFlux Fremont California USA

United States
Author Profile
Zhenyu Xu

Clemson University Clemson South Carolina USA

United States

📄 논문 정보

발행 연도 2025년
인용수 0
출판 국가 United States
사이트 ACM
좋아요 수 0

연관 논문 목록 (445건)