Page 269 - 《软件学报》2026年第2期

748 软件学报 2026 年第 37 卷第 2 期

3358922]
[16] Patra A, Suresh A. BLAZE: Blazing fast privacy-preserving machine learning. In: Proc. of the 2020 Network and Distributed System
Security (NDSS) Symp. San Diego, 2020. [doi: 10.14722/ndss.2020.24202]
[17] Beaver D. Efficient multiparty protocols using circuit randomization. In: Proc. of the Advances in Cryptology—CRYPTO 1991. Berlin:
Springer, 1992. 420–432. [doi: 10.1007/3-540-46766-1_34]
[18] Knott B, Venkataraman S, Hannun A, Sengupta S, Ibrahim M, van der Maaten L. CrypTen: Secure multi-party computation meets
machine learning. In: Proc. of the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 4961–4973.
[19] Kumar N, Rathee M, Chandran N, Gupta D, Rastogi A, Sharma R. CrypTFlow: Secure TensorFlow inference. In: Proc. of the 2020 IEEE
Symp. on Security and Privacy (SP). San Francisco: IEEE, 2020. 336–353. [doi: 10.1109/SP40000.2020.00092]
[20] Watson JL, Wagh S, Popa RA. Piranha: A GPU platform for secure computation. In: Proc. of the 31st USENIX Security Symp. Boston:
USENIX Association, 2022. 827–844.
[21] Keller M, Sun K. Secure quantized training for deep learning. In: Proc. of the 39th Int’l Conf. on Machine Learning. Baltimore: PMLR,
2022. 10912–10938.
[22] Jawalkar N, Gupta K, Basu A, Chandran N, Gupta D, Sharma R. Orca: FSS-based secure training and inference with GPUs. In: Proc. of
the 2024 IEEE Symp. on Security and Privacy (SP). San Francisco: IEEE, 2024. 597–616. [doi: 10.1109/SP54263.2024.00063]
[23] Jiang WX, Song XJ, Hong SB, Zhang HJ, Liu WX, Zhao B, Xu W, Li Y. Spin: An efficient secure computation framework with GPU
acceleration. arXiv:2402.02320, 2024.
[24] Araki T, Furukawa J, Lindell Y, Nof A, Ohara K. High-throughput semi-honest secure three-party computation with an honest majority.
In: Proc. of the 2016 ACM SIGSAC Conf. on Computer and Communications Security. Vienna: ACM, 2016. 805–817. [doi: 10.1145/
2976749.2978331]
[25] Chellapilla K, Puri S, Simard P. High performance convolutional neural networks for document processing. 2006. https://inria.hal.science/
inria-00112631/
[26] Canetti R. Universally composable security: A new paradigm for cryptographic protocols. In: Proc. of the 42nd IEEE Symp. on
Foundations of Computer Science. Newport Beach: IEEE, 2001. 136–145. [doi: 10.1109/SFCS.2001.959888]
[27] LeCun Y, Cortes C, Burges C. MNIST handwritten digit database. 2025. http://yann.lecun.com/exdb/mnist
[28] Krizhevsky A, Nair V, Hinton G. The CIFAR-10 dataset. 2014. http://www.cs.toronto.edu/kriz/cifar.html
[29] Le Y, Yang X. Tiny ImageNet visual recognition challenge. Stanford Course CS231N report. 2015. http://vision.stanford.edu/teaching/
cs231n/reports/2015/pdfs/yle_project.pdf
[30] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc. of the IEEE, 1998, 86(11):
2278–2324. [doi: 10.1109/5.726791]
[31] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Communications of the ACM,
2017, 60(6): 84–90. [doi: 10.1145/3065386]
[32] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, 2015.

作者简介
余欢, 硕士, 主要研究领域为基于秘密分享的隐私保护机器学习.
华强胜, 博士, 教授, CCF 杰出会员, 主要研究领域为并行分布式计算理论, 算法及应用.
卢必然, 本科生, 主要研究领域为密码学软硬件协同加速.
石宣化, 博士, 教授, CCF 杰出会员, 主要研究领域为智能计算, 异构计算, 大数据处理.
金海, 博士, 教授, CCF 会士, 主要研究领域为计算机体系结构, 并行与分布式处理, 虚拟化技术与云计算, 大数据, 算力网, 网络安全.