CryptoDB
SHAPER: A General Architecture for Privacy-Preserving Primitives in Secure Machine Learning
Authors: |
|
---|---|
Download: | |
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 }