Efficient Model Collaborative Training and Sharing Scheme of Blockchain Based on Hybrid Privacy
-
摘要: 针对海量数据下，基于区块链的联邦学习数据共享平台面临的效率低下和隐私泄露问题，该文提出基于混合隐私的区块链高效模型协同训练共享方案。在该方案中，首先根据欧氏距离设计了一种基于相似度的训练成员选择算法来选择训练成员，组成联邦社区，即通过选取少量的高匹配训练节点来提高训练的效率和效果。然后，结合阈值同态加密和差分隐私，设计一种基于混合隐私技术的模型协同训练共享方案来保证训练和共享过程中的隐私性。实验结果和系统实现表明，所提方案可以在保证训练结果准确率的情况下，实现高效训练和隐私保护下的数据共享。Abstract: Considering the problems of inefficiency and privacy leakage faced by the blockchain-based federated learning data sharing platform under massive data, an efficient model collaborative training and sharing scheme of blockchain based on hybrid privacy is proposed. In this scheme, a similarity-based training member selection algorithm according to Euclidean distance is first designed to select training members, forming a federated community, that is, to improve the efficiency and effect of training by selecting a small number of high-matching training nodes. Then, combined with threshold homomorphic encryption and differential privacy, a model collaborative training and sharing scheme based on hybrid privacy technology is constructed to ensure the privacy in the training and sharing process. The experimental results and system implementation show that the proposed scheme can achieve efficient training and data sharing under privacy protection while ensuring the accuracy of the training results.
-
Key words:
- Blockchain /
- Federated learning /
- Threshold homomorphic encryption /
- Differential privacy
-
算法1 基于相似度的训练成员选择算法 输入：数据共享请求$R = \{ Q,C{{ = (} }C_{{1} }^q,C_2^q,\cdots,C_{ {n} }^q{{)} }\}$，所有数据
拥有者$ P $的对应摘要集合$A{\mathbf{ = (} }{A_{{1} } },{A_{{2} } },\cdots,{A_N}{{)} }$，其中
${A_i}{{ = (} }{C_{i{{1} } } },{C_{i2} },\cdots,{C_{in} }{{)} }$；联邦社区成员个数$ h $输出：联邦学习社区成员$F{{ = (} }{P_{{1} } },{P_{{2} } },\cdots,{P_h}{{)} }$ 初始化$F{{[\;] = \{ 0\} } }$, $r = s = 0$ for $ i = 1;i < N + 1;i + + $ do for $j = 1;j < n + 1;j + + $ do $ r = {(C_1^q - {C_{ij}})^2} $ $ s = s + r $ end for $ S({P^q},{P_i}) = \sqrt s $ $S({P^q},{P_i}) \to F{{[\;]} }$ end for ${\text{Rank} }(F{{[\;]} })$ 从$ F{\mathbf{[]}} $中选取前$ h $个数据拥有者组成$F{\mathbf{ = (} }{P_{{1} } },{P_{{2} } },\cdots,{P_h}{{)} }$ return $F{\mathbf{ = (} }{P_{{1} } },{P_{{2} } },\cdots,{P_h}{{)} }$ 
下载: 导出CSV
-
[1] KASUBI J W, MANJAIAH D H, and DEMEWEZ G D. A review on the internet of things and big data analytics based on smart cities[C]. 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), Coimbatore, India, 2021: 1352–1358. [2] LV Zhihan, LOU Ranran, LI Jinhua, et al. Big data analytics for 6G-enabled massive internet of things[J]. IEEE Internet of Things Journal, 2021, 8(7): 5350–5359. doi: 10.1109/JIOT.2021.3056128 [3] DINH T N, SHEN Yilin, and THAI M T. The walls have ears: Optimize sharing for visibility and privacy in online social networks[C]. The 21st ACM International Conference on Information and Knowledge Management, Hawaii, USA, 2012: 1452–1461. [4] LIU Chi, ZHU Tianqing, ZHANG Jun, et al. Privacy intelligence: A survey on image sharing on online social networks[J]. arXiv preprint arXiv: 2008.12199, 2020. [5] ALEDHARI M, RAZZAK R, PARIZI R M, et al. Federated learning: A survey on enabling technologies, protocols, and applications[J]. IEEE Access, 2020, 8: 140699–140725. doi: 10.1109/ACCESS.2020.3013541 [6] YANG Hui, YUAN Jiaqi, LI Chao, et al. BrainIoT: Brain-like productive services provisioning with federated learning in industrial IoT[J]. IEEE Internet of Things Journal, 2022, 9(3): 2014–2024. doi: 10.1109/JIOT.2021.3089334 [7] YANG Hui, LIANG Yongshen, YUAN Jiaqi, et al. Distributed blockchain-based trusted multidomain collaboration for mobile edge computing in 5G and beyond[J]. IEEE Transactions on Industrial Informatics, 2020, 16(11): 7094–7104. doi: 10.1109/TII.2020.2964563 [8] YANG Hui, YUAN Jiaqi, YAO Haipeng, et al. Blockchain-based hierarchical trust networking for JointCloud[J]. IEEE Internet of Things Journal, 2020, 7(3): 1667–1677. doi: 10.1109/JIOT.2019.2961187 [9] LI Chao, YANG Hui, BAO Bowen, et al. A secure device access based on Blockchain for IoT in smart city[C]. 2021 International Wireless Communications and Mobile Computing (IWCMC), Harbin City, China, 2021: 1172–1174. [10] YANG Hui, BAO Bowen, LI Chao, et al. Blockchain-enabled tripartite anonymous identification trusted service provisioning in industrial IoT[J]. IEEE Internet of Things Journal, 2022, 9(3): 2419–2431. doi: 10.1109/JIOT.2021.3097440 [11] LI Chao, YANG Hui, SUN Zhengjie, et al. Federated hierarchical trust-based interaction scheme for cross-domain industrial IoT[J/OL]. IEEE Internet of Things Journal, 2022, https://ieeexplore.ieee.org/document/9865221, 2022. [12] ZHANG Xu and HOU Haibo. Application of federated learning in industrial internet with device identifier[C]. 2021 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), Chengdu, China, 2021: 1–5 [13] 陈乃月, 金一, 李浥东, 等. 基于区块链的公平性联邦学习模型[J]. 计算机工程, 2022, 48(6): 33–41. doi: 10.19678/j.issn.1000-3428.0064095CHEN Naiyue, JIN Yi, LI Yidong, et al. Federated learning model with fairness based on Blockchain[J]. Computer Engineering, 2022, 48(6): 33–41. doi: 10.19678/j.issn.1000-3428.0064095 [14] WENG Jiasi, WENG Jian, ZHANG Jilian, et al. DeepChain: Auditable and privacy-preserving deep learning with Blockchain-based incentive[J]. IEEE Transactions on Dependable and Secure Computing, 2021, 18(5): 2438–2455. doi: 10.1109/TDSC.2019.2952332 [15] QI Yuanhang, HOSSAIN M S, NIE Jiangtian, et al. Privacy-preserving blockchain-based federated learning for traffic flow prediction[J]. Future Generation Computer Systems, 2021, 117: 328–337. doi: 10.1016/j.future.2020.12.003 [16] 汤凌韬, 王迪, 张鲁飞, 等. 基于安全多方计算和差分隐私的联邦学习方案[J]. 计算机科学, 2022, 49(9): 297–305. doi: 10.11896/jsjkx.210800108TANG Lingtao, WANG Di, ZHANG Lufei, et al. Federated learning scheme based on secure multi-party computation and differential privacy[J]. Computer Science, 2022, 49(9): 297–305. doi: 10.11896/jsjkx.210800108 [17] TRUEX S, BARACALDO N, ANWAR A, et al. A hybrid approach to privacy-preserving federated learning[C]. Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, London, UK, 2019: 1–11. [18] SHE Wei, LIU Qi, TIAN Zhao, et al. Blockchain trust model for malicious node detection in wireless sensor networks[J]. IEEE Access, 2019, 7: 38947–38956. doi: 10.1109/ACCESS.2019.2902811 [19] 柴迪. 阈值同态加密在隐私计算中的应用[J]. 信息通信技术与政策, 2021, 47(7): 82–86. doi: 10.12267/j.issn.2096-5931.2021.07.012CHAI Di. Application of threshold homomorphic encryption in privacy computing[J]. Information and Communications Technology and Policy, 2021, 47(7): 82–86. doi: 10.12267/j.issn.2096-5931.2021.07.012 [20] GENG Ziye, HE Yunhua, WANG Chao, et al. A Blockchain based privacy-preserving reputation scheme for cloud service[C]. ICC 2021 - IEEE International Conference on Communications, Montreal, Canada, 2021: 1–6. -
图(9) / 表(1)
计量
- 文章访问数: 583
- HTML全文浏览量: 273
- PDF下载量: 132
- 被引次数: 0
下载:
