International Association for Cryptologic Research

International Association
for Cryptologic Research

CryptoDB

SHAPER: A General Architecture for Privacy-Preserving Primitives in Secure Machine Learning

Authors:
Ziyuan Liang , Zhejiang University, Hangzhou, China
Qi’ao Jin , Zhejiang University, Hangzhou, China
Zhiyong Wang , Zhejiang University, Hangzhou, China
Zhaohui Chen , Peking University, Beijing, China; DAMO Academy, Alibaba group, Beijing, China; Hupan Lab, Hangzhou, China
Zhen Gu , DAMO Academy, Alibaba group, Beijing, China; Hupan Lab, Hangzhou, China; Tsinghua University, Beijing, China
Yanhheng Lu , Hupan Lab, Hangzhou, China; Alibaba Group, Shanghai, China
Fan Zhang , Zhejiang University, Hangzhou, China
Download:
DOI: 10.46586/tches.v2024.i2.819-843
URL: https://tches.iacr.org/index.php/TCHES/article/view/11448
Search ePrint
Search Google
Abstract: Secure multi-party computation and homomorphic encryption are two primary security primitives in privacy-preserving machine learning, whose wide adoption is, nevertheless, constrained by the computation and network communication overheads. This paper proposes a hybrid Secret-sharing and Homomorphic encryption Architecture for Privacy-pERsevering machine learning (SHAPER). SHAPER protects sensitive data in encrypted or randomly shared domains instead of relying on a trusted third party. The proposed algorithm-protocol-hardware co-design methodology explores techniques such as plaintext Single Instruction Multiple Data (SIMD) and fine-grained scheduling, to minimize end-to-end latency in various network settings. SHAPER also supports secure domain computing acceleration and the conversion between mainstream privacy-preserving primitives, making it ready for general and distinctive data characteristics. SHAPER is evaluated by FPGA prototyping with a comprehensive hyper-parameter exploration, demonstrating a 94x speed-up over CPU clusters on large-scale logistic regression training tasks.
BibTeX
@article{tches-2024-34071,
  title={SHAPER: A General Architecture for Privacy-Preserving Primitives in Secure Machine Learning},
  journal={IACR Transactions on Cryptographic Hardware and Embedded Systems},
  publisher={Ruhr-Universität Bochum},
  volume={024 No. 2},
  pages={819-843},
  url={https://tches.iacr.org/index.php/TCHES/article/view/11448},
  doi={10.46586/tches.v2024.i2.819-843},
  author={Ziyuan Liang and Qi’ao Jin and Zhiyong Wang and Zhaohui Chen and Zhen Gu and Yanhheng Lu and Fan Zhang},
  year=2024
}