基于门限同态加密的自适应联邦学习安全聚合方案

doi:10.11959/j.issn.1000-436x.2023140

Abstract

Abstract:

Aiming at the communication bottleneck problem when the current federated learning security aggregation algorithm was applied in a complex network environment, an adaptive federated learning secure aggregation scheme based on threshold homomorphic encryption was proposed.While protecting gradient privacy, users adaptively compress gradients based on the current available bandwidth, greatly reduced communication overhead for federated users.Furthermore, the new dynamic decryption task distribution algorithm and gradient combination algorithm were designed in the phase of aggregation gradient decryption, which relieved the user’s uplink communication pressure.The experimental results show that the proposed scheme can sharply reduce the amount of communication to 4% compared with the existing federated learning scheme with a trivial model accuracy loss of 1%.

Key words: federated learning, secure aggregation, gradient sampling, threshold homomorphic encryption

CLC Number:

TN92

Zhuo MA, Jiayu JIN, Yilong YANG, Yang LIU, Zuobin YING, Teng LI, Junwei ZHANG. Adaptive federated learning secure aggregation scheme based on threshold homomorphic encryption[J]. Journal on Communications, 2023, 44(7): 76-85.

Figures/Tables 9

参数	含义
T	解密门限
M	联邦模型参数个数
CR min	最小压缩率
skn	第n个用户持有的私钥
pk	门限同态加密公钥
N	用户总数
n	第n个用户
Dn	第n个用户的本地数据集
gn	第n个用户训练得到的梯度
$g_{n}^{'}$	第n个用户的采样梯度
$E (g_{n}^{'})$	第n个用户加密的采样梯度
E (gn)	展开的加密梯度
Kn	第n个用户的采样个数
E (ga)	加密的聚合梯度
D（E(ga)）	部分解密的聚合梯度
ga	聚合梯度

方案	通信复杂度	计算复杂度	存储开销
本文方案	$I (N c \bar{{CR}_{n}} + c T)$	$O (\bar{{CR}_{n}} M)$	$\bar{{CR}_{n}} M N c + M$
POSEIDON	2I(N-1)c+(N-1)c	O(M+M log M)	MNc
HybirdAlpha	2NcI	O (M)	MNc

References 22

[1]	MANIAS D M , SHAMI A . Making a case for federated learning in the Internet of vehicles and intelligent transportation systems[J]. IEEE Network, 2021,35(3): 88-94.
[2]	莫梓嘉, 高志鹏, 杨杨 ,等. 面向车联网数据隐私保护的高效分布式模型共享策略[J]. 通信学报, 2022,43(4): 83-94.
	MO Z J , GAO Z P , YANG Y ,et al. Efficient distributed model sharing strategy for data privacy protection in Internet of vehicles[J]. Journal on Communications, 2022,43(4): 83-94.
[3]	KAISSIS G A , MAKOWSKI M R , RüCKERT D , ,et al. Secure,privacy-preserving and federated machine learning in medical imaging[J]. Nature Machine Intelligence, 2020,2(6): 305-311.
[4]	NGUYEN D C , DING M , PATHIRANA P N ,et al. Federated learning for Internet of things:a comprehensive survey[J]. IEEE Communications Surveys ＆ Tutorials, 2021,23(3): 1622-1658.
[5]	MCMAHAN B , MOORE E , RAMAGE D ,et al. Communication-efficient learning of deep networks from decentralized data[C]// Proceedings of Artificial Intelligence and Statistics. New York:PMLR, 2017: 1273-1282.
[6]	ZHU L , LIU Z , HAN S . Deep leakage from gradients[J]. arXiv Preprint,arXiv:1906.08935, 2019.
[7]	BONAWITZ K , IVANOV V , KREUTER B ,et al. Practical secure aggregation for privacy-preserving machine learning[C]// Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. New York:ACM Press, 2017: 1175-1191.
[8]	TRUEX S , BARACALDO N , ANWAR A ,et al. A hybrid approach to privacy-preserving federated learning[J]. Informatik Spektrum, 2019,42(5): 356-357.
[9]	LIU Y , MA Z , LIU X M ,et al. Boosting privately:privacy-preserving federated extreme boosting for mobile crowdsensing[J]. arXiv Preprint,arXiv:1907.10218, 2019.
[10]	AJI A F , HEAFIELD K . Sparse communication for distributed gradient descent[J]. arXiv Preprint,arXiv:1704.05021, 2017.
[11]	ZHAO Y K , ZHANG Y D , LI Y P ,et al. MinMax sampling:a near-optimal global summary for aggregation in the wide area[C]// Proceedings of the 2022 International Conference on Management of Data.[S.l.:s.n.], 2022: 744-758.
[12]	李尤慧子, 殷昱煜, 高洪皓 ,等. 面向隐私保护的非聚合式数据共享综述[J]. 通信学报, 2021,42(6): 195-212.
	LI Y H Z , YIN Y Y , GAO H H ,et al. Survey on privacy protection in non-aggregated data sharing[J]. Journal on Communications, 2021,42(6): 195-212.
[13]	TAHIR M , ALI M I . On the performance of federated learning algorithms for IoT[J]. IoT, 2022,3(2): 273-284.
[14]	HOSSEINALIPOUR S , BRINTON C G , AGGARWAL V ,et al. From federated to fog learning:distributed machine learning over heterogeneous wireless networks[J]. IEEE Communications Magazine, 2020,58(12): 41-47.
[15]	REISIZADEH A , TZIOTIS I , HASSANI H ,et al. Straggler-resilient federated learning:leveraging the interplay between statistical accuracy and system heterogeneity[J]. arXiv Preprint,arXiv:2012.14453, 2020.
[16]	LI T , SAHU A K , ZAHEER M ,et al. Federated optimization in heterogeneous networks[J]. arXiv Preprint,arXiv:1812.06127, 2018.
[17]	HSIEH K , HARLAP A , VIJAYKUMAR N ,et al. Gaia:GEO-distributed machine learning approaching LAN speeds[C]// Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation. Berkeley:USENIX Association, 2017: 629-647.
[18]	SAV S , PYRGELIS A , TRONCOSO-PASTORIZA J R , ,et al. POSEIDON:privacy-preserving federated neural network learning[J]. arXiv Preprint,arXiv:2009.00349, 2020.
[19]	XU R H , BARACALDO N , ZHOU Y ,et al. HybridAlpha:an efficient approach for privacy-preserving federated learning[C]// Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security. New York:ACM Press, 2019: 13-23.
[20]	DAMGRD I , JURIK M . A generalisation,a simplification and some applications of paillier’s probabilistic public-key system[C]// International Workshop on Public Key Cryptography. Berlin:Springer, 2001: 119-136.
[21]	KATZ J , LINDELL Y . Introduction to modern cryptography[M]. Boca Raton: CRC Press, 2020.
[22]	HITAJ B , ATENIESE G , PEREZ-CRUZ F . Deep models under the GAN:information leakage from collaborative deep learning[C]// Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. New York:ACM Press, 2017: 603-618.

Metrics

Recommended 0

No Suggested Reading articles found!

组别	压缩率分配方案（个数:压缩率）	平均压缩率
CR₁	100:1	1
CR₂	100:0.1	0.1
CR₃	50:0.1，50:0.05	0.075
CR₄	33:0.1，33:0.05，34:0.005	0.051 2
CR₅	25:0.1，25:0.05，25:0.005，25:0.001	0.039
CR₆	100:0.001	0.001
CR₇	100:0.039	0.039

Adaptive federated learning secure aggregation scheme based on threshold homomorphic encryption

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 22

Related Articles 15

Metrics

Recommended 0

[1]	Xindi MA, Qinghua LI, Qi JIANG, Zhuo MA, Sheng GAO, Youliang TIAN, Jianfeng MA. Byzantine-robust federated learning over Non-IID data [J]. Journal on Communications, 2023, 44(6): 138-153.
[2]	Jiale ZHANG, Chengcheng ZHU, Xiaobing SUN, Bing CHEN. Membership inference attack and defense method in federated learning based on GAN [J]. Journal on Communications, 2023, 44(5): 193-205.
[3]	Youliang TIAN, Shihong WU, Ta LI, Lindong WANG, Hua ZHOU. Federated learning optimization algorithm based on incentive mechanism [J]. Journal on Communications, 2023, 44(5): 169-180.
[4]	Hui JIANG, Tianliu HE, Min LIU, Sheng SUN, Yuwei WANG. High-performance federated continual learning algorithm for heterogeneous streaming data [J]. Journal on Communications, 2023, 44(5): 123-136.
[5]	Shengxing YU, Zekai CHEN, Zhong CHEN, Ximeng LIU. DAGUARD: distributed backdoor attack defense scheme under federated learning [J]. Journal on Communications, 2023, 44(5): 110-122.
[6]	Kaiju LI, Qiang XU, Hao WANG. Communication-efficient federated learning method via redundant data elimination [J]. Journal on Communications, 2023, 44(5): 79-93.
[7]	Shengxing YU, Zhong CHEN. Efficient secure federated learning aggregation framework based on homomorphic encryption [J]. Journal on Communications, 2023, 44(1): 14-28.
[8]	Lingtao TANG, Di WANG, Shengyun LIU. Data augmentation scheme for federated learning with non-IID data [J]. Journal on Communications, 2023, 44(1): 164-176.
[9]	Shaoshuai FAN, Jianbo WU, Hui TIAN. Federated learning resource management for energy-constrained industrial IoT devices [J]. Journal on Communications, 2022, 43(8): 65-77.
[10]	Zijia MO, Zhipeng GAO, Yang YANG, Yijing LIN, Shan SUN, Chen ZHAO. Efficient distributed model sharing strategy for data privacy protection in Internet of vehicles [J]. Journal on Communications, 2022, 43(4): 83-94.
[11]	Haiyan KANG, Yuanrui JI. Research on federated learning approach based on local differential privacy [J]. Journal on Communications, 2022, 43(10): 94-105.
[12]	Youhuizi LI, Yuyu YIN, Honghao GAO, Yi JIN, Xinheng WANG. Survey on privacy protection in non-aggregated data sharing [J]. Journal on Communications, 2021, 42(6): 195-212.
[13]	Wenchen HE, Shaoyong GUO, Xuesong QIU, Liandong CHEN, Suxiang ZHANG. Node selection method in federated learning based on deep reinforcement learning [J]. Journal on Communications, 2021, 42(6): 62-71.
[14]	Meixia TAO, Dong WANG, Rui SUN, Naifu ZHANG. TDMA-based user scheduling policies for federated learning [J]. Journal on Communications, 2021, 42(6): 1-29.
[15]	Yongming HUANG, Chong ZHENG, Zhengming ZHANG, Xiaohu YOU. Research on mobile edge computing and caching in massive wireless communication network [J]. Journal on Communications, 2021, 42(4): 44-61.