Page 351 - 《软件学报》2026年第6期

2670 软件学报 2026 年第 37 卷第 6 期

SIGSAC Conf. on Computer and Communications Security. Dallas: ACM, 2017. 619–631. [doi: 10.1145/3133956.3134056]
[17] 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. ACM, 2021. 379.
[18] Avci O, Abdeljaber O, Kiranyaz S, Hussein M, Gabbouj M, Inman DJ. A review of vibration-based damage detection in civil structures:
From traditional methods to machine learning and deep learning applications. Mechanical Systems and Signal Processing, 2021, 147:
107077. [doi: 10.1016/j.ymssp.2020.107077]
[19] Hao M, Li HW, Chen HX, Xing PZ, Zhang TW. FastSecNet: An efficient cryptographic framework for private neural network inference.
IEEE Trans. on Information Forensics and Security, 2023, 18: 2569–2582. [doi: 10.1109/TIFS.2023.3262149]
[20] Hesamifard E, Takabi H, Ghasemi M. CryptoDL: Deep neural networks over encrypted data. arXiv:1711.05189, 2017.
[21] Brutzkus A, Gilad-Bachrach R, Elisha O. Low latency privacy preserving inference. In: Proc. of the 36th Int’l Conf. on Machine
Learning. Long Beach: PMLR, 2019. 812–821.
[22] Riazi MS, Samragh M, Chen H, Laine K, Lauter K, Koushanfar F. XONN: XNOR-based oblivious deep neural network inference. In:
Proc. of the 28th USENIX Conf. on Security Symp. Santa Clara: ACM, 2019. 1501–1518.
[23] Li SH, Xue KP, Zhu B, Ding CK, Gao XD, Wei D, Wan T. FALCON: A Fourier transform based approach for fast and secure
convolutional neural network predictions. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle:
IEEE, 2020. 8702–8711. [doi: 10.1109/CVPR42600.2020.00873]
[24] Bian S, Wang TC, Hiromoto M, Shi YY, Sato T. ENSEI: Efficient secure inference via frequency-domain homomorphic convolution for
privacy-preserving visual recognition. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE,
2020. 9400–9409. [doi: 10.1109/CVPR42600.2020.00942]
[25] 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. San Francisco: IEEE, 2020. 336–353. [doi: 10.1109/SP40000.2020.00092]
[26] Ghodsi Z, Jha NK, Reagen B, Garg S. Circa: Stochastic ReLUs for private deep learning. In: Proc. of the 35th Int’l Conf. on Neural
Information Processing Systems. ACM, 2021. 172.
[27] Hussain SU, Javaheripi M, Samragh M, Koushanfar F. COINN: Crypto/ML codesign for oblivious inference via neural networks. In:
Proc. of the 2021 ACM SIGSAC Conf. on Computer and Communications Security. ACM, 2021. 3266–3281. [doi: 10.1145/3460120.
3484797]
[28] Kim D, Guyot C. Optimized privacy-preserving CNN inference with fully homomorphic encryption. IEEE Trans. on Information
Forensics and Security, 2023, 18: 2175–2187. [doi: 10.1109/TIFS.2023.3263631]
[29] Beimel A. Secret-sharing schemes: A survey. In: Proc. of the 3rd Int’l Conf. on Coding and Cryptology. Qingdao: Springer, 2011. 11–46.
[doi: 10.1007/978-3-642-20901-7_2]
[30] Hu J, Shen L, Albanie S, Sun G, Wu EH. Squeeze-and-excitation networks. IEEE Trans. on Pattern Analysis and Machine Intelligence,
2020, 42(8): 2011–2023. [doi: 10.1109/TPAMI.2019.2913372]
[31] Liu JX, Meng XF. Survey on privacy-preserving machine learning. Journal of Computer Research and Development, 2020, 57(2):
346–362 (in Chinese with English abstract). [doi: 10.7544/issn1000-1239.2020.20190455]

附中文参考文献
[8] 宋蕾, 马春光, 段广晗. 机器学习安全及隐私保护研究进展. 网络与信息安全学报, 2018, 4(8): 1–11. [doi: 10.11959/j.issn.2096-109x.
2018067]
[31] 刘俊旭, 孟小峰. 机器学习的隐私保护研究综述. 计算机研究与发展, 2020, 57(2): 346–362. [doi: 10.7544/issn1000-1239.2020.
20190455]

作者简介
白浩, 博士生, 主要研究领域为隐私保护机器学习.
何琨, 博士, 副教授, CCF 专业会员, 主要研究领域为应用密码学, 网络安全, 云计算安全, 人工智能安全, 区块链安全.
陈晶, 博士, 教授, 博士生导师, CCF 高级会员, 主要研究领域为网络安全, 分布式系统安全, 区块链.
赵陈斌, 博士生, 主要研究领域为应用密码学, 可搜索加密.
杜瑞颖, 博士, 教授, 博士生导师, 主要研究领域为网络安全, 隐私保护.