Research on vertical federated learning based on secret sharing and homomorphic encryption

doi:10.12267/j.issn.2096-5931.2021.06.003

Abstract

Abstract: Due to the promulgation of more and more privacy protection policies, many privacy preserving computing algorithms are developed. Among them, federated learning is practical in building machine learning algorithms under privacy preserving computing. This article, introduces different federated learning frameworks for different datapartition case, and demonstrates vertical federated learning with logistic regression as an example. Finally, it introduces the pros and cons of different implementations and their applicable scene.

Key words: privacy preserving computing, federated learning, multi-party computation, homomorphic encryption, secret sharing

XIA Jiajun, LU Ying, ZHANG Ziyang, ZHANG Yuting, ZHANG Jiachen. Research on vertical federated learning based on secret sharing and homomorphic encryption[J]. Information and Communications Technology and Policy, 2021, 47(6): 19-26.

Add to citation manager EndNote|Ris|BibTeX

URL:

http://ictp.caict.ac.cn/EN/10.12267/j.issn.2096-5931.2021.06.003

http://ictp.caict.ac.cn/EN/Y2021/V47/I6/19

References 13

[1]	General. Data protection regulation [EB / OL]. (2018)[2021-03-20]. https:/ / eur-lex. europa. eu / legal-content /EN / TXT / PDF / ? uri =CELEX:32016R0679.
[2]	Mcmahan H B, Moore E, Ramage D, et al.Federatedlearning of deep networks using model averaging
[C]	Proceedings of the 20 th International Conference on Artificial Intelligence and Statistics ( AISTATS ),
	2017.
[3]	YANG Q, LIU Y, CHEN T, et al. Federated machine learning: conceptand applications [ C ]. arXiv, 2019:
19	02. 04885.
[4]	Kairouz P, McMahan H B, Avent B, et al. Advances and openproblems in federated learning[C]. ACM Transactions
	on Intelligent Systems and Technology ( TIST ), 2019(12).
[5]	Hard A, Rao K, Mathews R, et al. Federated learning for mobile keyboardprediction [ C ]. arXiv, 2018: 1811.03604.
[6]	Bonawitz Keith, Ivanov Vladimir, Kreuter Ben, et al.Practicalsecure aggregation for privacy-preserving machine learning[C]. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS’17). Association for Computing Machinery, New York, NY, USA, 2017:1175 – 1191.
[ 7 ]	McMahan H B, Moore E, Ramage D, et al. Communication-efficient learning of deep networks from
	decentralizeddata [ C ], Proceedings of the 20th International Conference on ArtificialIntelligence and
	Statistics, AISTATS, 2017.
[8]	YIN Hongxu, Arun Mallya, Arash Vahdat, et al. See through gradients: image batch recovery via gradInversion[C]. arXiv preprint arXiv, 2021:07586.
[9]	Wei K, Li J, Ding M, et al. Federated learning with differential privacy: algorithms and performance analysis
[C]	, IEEE Transactions on Information Forensics and Security, 2020(15): 3454-3469.
[10]	Yang L , Chen T , Qiang Y. Secure federated transfer learning[C], ArXiv, abs / 1812. 03337.
[11]	Sharma S , Chaoping X , Liu Y , et al. Secure and efficient federated transfer learning [ C ] / / 2019 IEEE
	International Conference on Big Data, 2569-2576.
[12]	Paillier P. Public-key cryptosystems based on composite degree residuosity classes[C]. Proc EUROCRYPT􀆳99, Czech Republic, 1999.
[13]	Beaver D. Efficient Multiparty Protocols Using Circuit Randomization [ C ] / / Advances in Cryptology- CRYPTO􀆳91, 11th Annual International Cryptology Conference, 1991(8):11-15.

[1]	YAN Shu, LYU Ailin. Overview of the development of privacy preserving computing [J]. Information and Communications Technology and Policy, 2021, 47(6): 1-11.
[2]	YUAN Bo, WANG Siyuan. Privacy preserving computing product evaluation system [J]. Information and Communications Technology and Policy, 2021, 47(6): 12-18.
[3]	FU Fangcheng, HOU Chen, CHENG Yong, TAO Yangyu. Key technology and innovation of privacy preserving computing [J]. Information and Communications Technology and Policy, 2021, 47(6): 27-37.
[4]	XU Qian, ZHANG Qing, YU Bo, YU Wenqing, HE Wei. Middleware and blockchain based interconnecting system of heterogeneous privacy preserving computing platforms [J]. Information and Communications Technology and Policy, 2021, 47(6): 38-49.
[5]	HUANG Cuiting, ZHANG Fan, SUN Xiaochao, BIAN Yang. A survey of Private Set Intersection technology and finance practice [J]. Information and Communications Technology and Policy, 2021, 47(6): 50-.
[6]	QIANG Feng, XUE Yushan, XIANG Mei. Privacy preserving computing in the financial field [J]. Information and Communications Technology and Policy, 2021, 47(6): 57-62.
[7]	CHENG Qiang, LIU Zishan. Intelligent telecommunication networks: current status and future prospects [J]. Information and Communications Technology and Policy, 2020, 46(9): 16-22.
[8]	LI Jian, SHAO Yunfeng, LU Yi, WU Jun. Overview of federal learning and its application in telecom industry [J]. Information and Communications Technology and Policy, 2020, 46(9): 35-41.
[9]	FENG Haoming, CHEN Hang, LIU Yanping. Ablockchain asset trading system based on homomorphic encryption and ring signature [J]. Information and Communications Technology and Policy, 2020, 46(1): 64-68.