《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (2): 506-517.DOI: 10.11772/j.issn.1001-9081.2024020249
• 网络空间安全 • 上一篇
陈海田1,2,3, 陈学斌1,2,3(), 马锐奎1,2, 张帅华1,2,3
收稿日期:
2024-03-11
修回日期:
2024-04-03
接受日期:
2024-04-09
发布日期:
2024-06-04
出版日期:
2025-02-10
通讯作者:
陈学斌
作者简介:
陈海田(1998—),男,湖南娄底人,硕士研究生,CCF会员,主要研究方向:数据安全、隐私保护基金资助:
Haitian CHEN1,2,3, Xuebin CHEN1,2,3(), Ruikui MA1,2, Shuaihua ZHANG1,2,3
Received:
2024-03-11
Revised:
2024-04-03
Accepted:
2024-04-09
Online:
2024-06-04
Published:
2025-02-10
Contact:
Xuebin CHEN
About author:
CHEN Haitian, born in 1998, M. S. candidate. His research interests include data security, privacy protection.Supported by:
摘要:
遥感数据具有高度的时空相关性以及复杂的地物特征,使得这些数据的隐私保护面临挑战。联邦学习作为一种旨在保护参与方数据隐私的分布式学习方法,为应对遥感数据隐私保护面对的挑战提供了有效的解决方案;然而,在联邦学习模型的训练阶段,恶意攻击者可能通过反演推断参与者的隐私信息,进而导致敏感信息的泄露。针对遥感数据在联邦学习训练中存在的隐私泄露问题,提出一种基于本地差分隐私的联邦学习隐私保护方案。首先,对模型进行预训练,计算模型的层重要性,并根据层重要性合理分配隐私预算;然后,通过对模型更新进行裁剪变换,并对裁剪值进行自适应随机扰动,实现本地差分隐私保护;最后,在聚合扰动更新时,采用模型校正以进一步提高模型性能。理论分析和仿真结果表明,所提方案不仅能为各参与方提供合适的差分隐私保护,并有效防止通过反演推断出隐私敏感信息,而且在3个遥感数据集上相较于基于分段机制的扰动方案提升了3.28~3.93个百分点的准确率。可见,所提方案在保证隐私的同时有效保障了模型性能。
中图分类号:
陈海田, 陈学斌, 马锐奎, 张帅华. 面向遥感数据的基于本地差分隐私的联邦学习隐私保护方案[J]. 计算机应用, 2025, 45(2): 506-517.
Haitian CHEN, Xuebin CHEN, Ruikui MA, Shuaihua ZHANG. Federated learning privacy protection scheme based on local differential privacy for remote sensing data[J]. Journal of Computer Applications, 2025, 45(2): 506-517.
数据集 | 图像尺寸 | 标签 类别数 | 图像数 | |||
---|---|---|---|---|---|---|
总数 | 训练集 | 测试集 | 验证集 | |||
EuroSAT | 10 | 27 000 | 18 900 | 5 400 | 2 700 | |
RSSCN7 | 7 | 2 800 | 1 960 | 560 | 280 | |
WHU-RS19 | 19 | 1 005 | 703 | 202 | 100 | |
UCMerced | 21 | 2 100 | 1 470 | 420 | 210 |
表1 实验中使用的遥感数据集
Tab. 1 Remote sensing datasets used in experiments
数据集 | 图像尺寸 | 标签 类别数 | 图像数 | |||
---|---|---|---|---|---|---|
总数 | 训练集 | 测试集 | 验证集 | |||
EuroSAT | 10 | 27 000 | 18 900 | 5 400 | 2 700 | |
RSSCN7 | 7 | 2 800 | 1 960 | 560 | 280 | |
WHU-RS19 | 19 | 1 005 | 703 | 202 | 100 | |
UCMerced | 21 | 2 100 | 1 470 | 420 | 210 |
扰动强度 | PSNR/dB | SSIM | MSE | LPIPS |
---|---|---|---|---|
1.00 | 8.810 7 | 0.002 6 | 2.094 2 | 0.854 1 |
0.20 | 9.107 8 | 0.004 5 | 1.955 7 | 0.833 4 |
0.05 | 26.708 7 | 0.272 2 | 0.033 9 | 0.436 4 |
0.02 | 30.523 9 | 0.489 9 | 0.014 1 | 0.261 1 |
0.00 | 33.499 7 | 0.612 7 | 0.007 1 | 0.168 5 |
表2 不同扰动强度下RSLDP-FL的防御性能指标对比
Tab. 2 Comparison of defense performance indicators of RSLDP-FL under different disturbance intensities
扰动强度 | PSNR/dB | SSIM | MSE | LPIPS |
---|---|---|---|---|
1.00 | 8.810 7 | 0.002 6 | 2.094 2 | 0.854 1 |
0.20 | 9.107 8 | 0.004 5 | 1.955 7 | 0.833 4 |
0.05 | 26.708 7 | 0.272 2 | 0.033 9 | 0.436 4 |
0.02 | 30.523 9 | 0.489 9 | 0.014 1 | 0.261 1 |
0.00 | 33.499 7 | 0.612 7 | 0.007 1 | 0.168 5 |
分配方式 | 数据集 | ||||
---|---|---|---|---|---|
自适应 分配 | EuroSAT | 39.61 | 77.37 | 88.89 | 89.74 |
WHU-RS19 | 37.67 | 75.42 | 83.57 | 84.42 | |
UCMerced | 44.35 | 82.61 | 89.74 | 91.19 | |
RSSCN7 | 15.51 | 72.14 | 83.67 | 84.82 | |
平均 分配 | EuroSAT | 31.57 | 69.14 | 82.11 | 86.84 |
WHU-RS19 | 30.14 | 65.28 | 77.57 | 81.68 | |
UCMerced | 34.89 | 72.65 | 84.48 | 88.33 | |
RSSCN7 | 13.28 | 59.28 | 78.42 | 82.09 |
表3 不同隐私预算分配对模型性能的影响 (%)
Tab. 3 Influence of different privacy budget allocation on model performance
分配方式 | 数据集 | ||||
---|---|---|---|---|---|
自适应 分配 | EuroSAT | 39.61 | 77.37 | 88.89 | 89.74 |
WHU-RS19 | 37.67 | 75.42 | 83.57 | 84.42 | |
UCMerced | 44.35 | 82.61 | 89.74 | 91.19 | |
RSSCN7 | 15.51 | 72.14 | 83.67 | 84.82 | |
平均 分配 | EuroSAT | 31.57 | 69.14 | 82.11 | 86.84 |
WHU-RS19 | 30.14 | 65.28 | 77.57 | 81.68 | |
UCMerced | 34.89 | 72.65 | 84.48 | 88.33 | |
RSSCN7 | 13.28 | 59.28 | 78.42 | 82.09 |
方案 | 数据集 | 准确率 | 精确度 | 召回率 | F1 |
---|---|---|---|---|---|
No-DP | EuroSAT | 93.85 | 93.61 | 93.47 | 93.48 |
UCMerced | 95.71 | 83.24 | 83.35 | 83.29 | |
RSSCN7 | 90.25 | 90.59 | 90.39 | 90.49 | |
LDP-FL_D | EuroSAT | 23.50 | 22.81 | 22.84 | 22.82 |
UCMerced | 22.61 | 13.44 | 19.38 | 15.61 | |
RSSCN7 | 18.97 | 19.08 | 16.01 | 16.15 | |
LDP-FL_P | EuroSAT | 86.46 | 86.26 | 85.84 | 86.04 |
UCMerced | 87.85 | 77.25 | 77.59 | 77.39 | |
RSSCN7 | 80.89 | 81.14 | 80.20 | 81.04 | |
LDP-FL_PS | EuroSAT | 88.53 | 88.26 | 88.03 | 88.18 |
UCMerced | 89.04 | 77.86 | 78.46 | 78.14 | |
RSSCN7 | 83.31 | 84.76 | 83.61 | 84.18 | |
RSLDP-FL | EuroSAT | 89.74 | 89.41 | 89.34 | 89.37 |
UCMerced | 91.19 | 79.25 | 79.90 | 79.57 | |
RSSCN7 | 84.82 | 85.18 | 84.05 | 85.09 |
表4 不同方案在不同遥感数据集上的测试结果 (%)
Tab. 4 Test results of different schemes on different remote sensing datasets
方案 | 数据集 | 准确率 | 精确度 | 召回率 | F1 |
---|---|---|---|---|---|
No-DP | EuroSAT | 93.85 | 93.61 | 93.47 | 93.48 |
UCMerced | 95.71 | 83.24 | 83.35 | 83.29 | |
RSSCN7 | 90.25 | 90.59 | 90.39 | 90.49 | |
LDP-FL_D | EuroSAT | 23.50 | 22.81 | 22.84 | 22.82 |
UCMerced | 22.61 | 13.44 | 19.38 | 15.61 | |
RSSCN7 | 18.97 | 19.08 | 16.01 | 16.15 | |
LDP-FL_P | EuroSAT | 86.46 | 86.26 | 85.84 | 86.04 |
UCMerced | 87.85 | 77.25 | 77.59 | 77.39 | |
RSSCN7 | 80.89 | 81.14 | 80.20 | 81.04 | |
LDP-FL_PS | EuroSAT | 88.53 | 88.26 | 88.03 | 88.18 |
UCMerced | 89.04 | 77.86 | 78.46 | 78.14 | |
RSSCN7 | 83.31 | 84.76 | 83.61 | 84.18 | |
RSLDP-FL | EuroSAT | 89.74 | 89.41 | 89.34 | 89.37 |
UCMerced | 91.19 | 79.25 | 79.90 | 79.57 | |
RSSCN7 | 84.82 | 85.18 | 84.05 | 85.09 |
方案 | 数据集 | 准确率 | 精确度 | 召回率 | F1 |
---|---|---|---|---|---|
No-LIC | EuroSAT | 86.84 | 86.60 | 86.51 | 86.55 |
UCMerced | 88.33 | 77.41 | 79.04 | 78.21 | |
RSSCN7 | 82.09 | 83.18 | 82.57 | 83.14 | |
No-MC | EuroSAT | 86.03 | 85.48 | 85.34 | 85.41 |
UCMerced | 86.71 | 76.25 | 77.19 | 76.68 | |
RSSCN7 | 81.83 | 82.09 | 81.25 | 81.66 |
表5 不同遥感数据集上消融实验对比结果 (%)
Tab. 5 Comparative results of ablation experiments on different remote sensing datasets
方案 | 数据集 | 准确率 | 精确度 | 召回率 | F1 |
---|---|---|---|---|---|
No-LIC | EuroSAT | 86.84 | 86.60 | 86.51 | 86.55 |
UCMerced | 88.33 | 77.41 | 79.04 | 78.21 | |
RSSCN7 | 82.09 | 83.18 | 82.57 | 83.14 | |
No-MC | EuroSAT | 86.03 | 85.48 | 85.34 | 85.41 |
UCMerced | 86.71 | 76.25 | 77.19 | 76.68 | |
RSSCN7 | 81.83 | 82.09 | 81.25 | 81.66 |
数据集 | 算法 | 准确率/% | 模型损失 |
---|---|---|---|
MNIST | No-DP | 92.225 | 0.316 |
RSLDP-FL | 84.112 | 0.557 | |
CIFAR-10 | No-DP | 70.599 | 0.906 |
RSLDP-FL | 63.974 | 1.092 |
表6 RSLDP-FL在MNIST和CIFAR-10数据集上的模型性能
Tab. 6 Model performance of RSLDP-FL on MNIST and CIFAR-10 datasets
数据集 | 算法 | 准确率/% | 模型损失 |
---|---|---|---|
MNIST | No-DP | 92.225 | 0.316 |
RSLDP-FL | 84.112 | 0.557 | |
CIFAR-10 | No-DP | 70.599 | 0.906 |
RSLDP-FL | 63.974 | 1.092 |
1 | 边小勇,费雄君,陈春芳,等. 联合一二阶池化网络学习的遥感场景分类[J]. 计算机应用, 2022, 42(6): 1972-1978. |
BIAN X Y, FEI X J. CHEN C F,et al. Joint 1-2-order pooling network learning for remote sensing scene classification[J]. Journal of Computer Applications, 2022, 42(6): 1972-1978. | |
2 | 梁敏,汪西莉. 结合超分辨率和域适应的遥感图像语义分割方法[J]. 计算机学报, 2022, 45(12): 2619-2636. |
LIANG M, WANG X L. Semantic segmentation model for remote sensing images combining super resolution and domain adaptation[J]. Chinese Journal of Computers, 2022, 45(12): 2619-2636. | |
3 | 张省,李山山,魏国芳,等. 面向精细化多尺度特征的遥感图像目标检测[J]. 遥感学报, 2022, 26(12): 2616-2628. |
ZHANG S, LI S S, WEI G F, et al. Refined multi-scale feature-oriented object detection of the remote sensing images[J]. National Remote Sensing Bulletin, 2022, 26(12): 2616-2628. | |
4 | ZHU J, WU J, BASHIR A K, et al. Privacy-preserving federated learning of remote sensing image classification with dishonest majority[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16: 4685-4698. |
5 | McMAHAN H B, MOORE E, RAMAGE D, et al. Communication-efficient learning of deep networks from decentralized data[C]// Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. New York: JMLR.org, 2017: 1273-1282. |
6 | 王波,李洪涛,王洁,等. 面向医疗数据的隐私保护联邦学习架构[J]. 西安电子科技大学学报, 2023, 50(5): 166-177. |
WANG B, LI H T, WANG J, et al. Federated learning scheme for privacy-preserving of medical data[J]. Journal of Xidian University, 2023, 50(5): 166-177. | |
7 | HU H, PENG R, TAI Y W, et al. Network trimming: a data-driven neuron pruning approach towards efficient deep architectures[EB/OL]. [2023-11-12].. |
8 | ZHAO Y, ZHAO J, YANG M, et al. Local differential privacy-based federated learning for internet of things[J]. IEEE Internet of Things Journal, 2021, 8(11): 8836-8853. |
9 | CHENG G, XIE X, HAN J, et al. Remote sensing image scene classification meets deep learning: challenges, methods, benchmarks, and opportunities[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 3735-3756. |
10 | 屈震,李堃婷,冯志玺. 基于有效通道注意力的遥感图像场景分类[J]. 计算机应用, 2022, 42(5): 1431-1439. |
QU Z, LI K T, FENG Z X. Remote sensing image scene classification based on effective channel attention[J]. Journal of Computer Applications, 2022, 42(5): 1431-1439. | |
11 | 张昊,何灵敏,潘晨. 改进的SegFormer遥感图像语义分割网络[J]. 计算机工程与应用, 2023, 59(24): 248-258. |
ZHANG H, HE L M, PAN C. Improved SegFormer remote sensing image semantic segmentation network[J]. Computer Engineering and Applications, 2023, 59(24): 248-258. | |
12 | SONG Q, CAO J, LI Y, et al. On efficient federated learning for aerial remote sensing image classification: a filter pruning approach[C]// Proceedings of the 2023 International Conference on Neural Information Processing, LNCS 14450. Singapore: Springer, 2024: 184-199. |
13 | SHIVKUMAR S, PALANISWAMY S. Satellite image segmentation using federated learning: a privacy preserving approach[C]// Proceedings of the 7th International Conference on Computation System and Information Technology for Sustainable Solutions. Piscataway: IEEE, 2023: 1-6. |
14 | ZHANG X, ZHANG B, YU W, et al. Federated deep learning with prototype matching for object extraction from very-high-resolution remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: No.5603316. |
15 | 陈学斌,任志强,张宏扬. 联邦学习中的安全威胁与防御措施综述[J]. 计算机应用, 2024, 44(6):1663-1672. |
CHEN X B, REN Z Q, ZHANG H Y. Review on security threats and defense measures in federated learning[J]. Journal of Computer Applications, 2024, 44(6):1663-1672. | |
16 | 段昕汝,陈桂茸,陈爱网,等. 联邦学习中的信息安全问题研究综述[J]. 计算机工程与应用, 2024, 60(3): 61-77. |
DUAN X R, CHEN G R, CHEN A W, et al. Review of research on information security in federated learning[J]. Computer Engineering and Applications, 2024, 60(3): 61-77. | |
17 | NASR M, SHOKRI R, HOUMANSADR A. Comprehensive privacy analysis of deep learning: passive and active white-box inference attacks against centralized and federated learning[C]// Proceedings of the 2019 IEEE Symposium on Security and Privacy. Piscataway: IEEE, 2019: 739-753. |
18 | ZHAO B, MOPURI K R, BILEN H. iDLG: improved deep leakage from gradients[EB/OL]. [2023-11-12].. |
19 | ZHU L, LIU Z, HAN S. Deep leakage from gradients[C]// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2019: 14774-14784. |
20 | SONG M, WANG Z, ZHANG Z, et al. Analyzing user-level privacy attack against federated learning[J]. IEEE Journal on Selected Areas in Communications, 2020, 38(10): 2430-2444. |
21 | 张佳乐,朱诚诚,孙小兵,等. 基于GAN的联邦学习成员推理攻击与防御方法[J]. 通信学报, 2023, 44(5): 193-205. |
ZHANG J L, ZHU C C, SUN X B, et al. Membership inference attack and defense method in federated learning based on GAN[J]. Journal on Communications, 2023, 44(5): 193-205. | |
22 | 高莹,陈晓峰,张一余,等. 联邦学习系统攻击与防御技术研究综述[J]. 计算机学报, 2023, 46(9): 1781-1805. |
GAO Y, CHEN X F, ZHANG Y Y, et al. A review of research on attack and defense techniques for federated learning systems[J]. Chinese Journal of Computers, 2023, 46(9): 1781-1805. | |
23 | WANG T, ZHANG Y, JIA R. Improving robustness to model inversion attacks via mutual information regularization[C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021: 11666-11673. |
24 | PENG X, LIU F, ZHANG J, et al. Bilateral dependency optimization: defending against model-inversion attacks[C]// Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2022: 1358-1367. |
25 | SHEJWALKAR V, HOUMANSADR A. Membership privacy for machine learning models through knowledge transfer[C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021: 9549-9557. |
26 | 周辉,陈玉玲,王学伟,等. 基于生成对抗网络的联邦学习深度影子防御方案[J]. 计算机应用, 2024, 44(1): 223-232. |
ZHOU H, CHEN Y L, WANG X W, et al. Deep shadow defense scheme of federated learning based on generative adversarial network[J]. Journal of Computer Applications, 2024, 44(1): 223-232. | |
27 | LUO X, ZHANG X. Exploiting defenses against GAN-based feature inference attacks in federated learning[EB/OL]. [2024-10-12].. |
28 | JEGOROVA M, KAUL C, MAYOR C, et al. Survey: leakage and privacy at inference time[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(7): 9090-9108. |
29 | LIU Y, WEN R, HE X, et al. ML-Doctor: holistic risk assessment of inference attacks against machine learning models[C]// Proceedings of the 31st USENIX Security Symposium. Berkeley: USENIX Association, 2022: 4525-4542. |
30 | 张连福,谭作文. 一种面向多模态医疗数据的联邦学习隐私保护方法[J]. 计算机科学, 2023, 50(11A): No.230800021. |
ZHANG L F, TAN Z W. Federated learning privacy-preserving approach for multimodal medical data[J]. Computer Science, 2023, 50(11A): No.230800021. | |
31 | 于雅娜,李红娇,李晋国. 差分隐私保护WGAN-GP算法研究[J]. 计算机应用研究, 2021, 38(9): 2837-2841. |
YU Y N, LI H J, LI J G. Research on differential privacy protection for WGAN-GP algorithm[J]. Application Research of Computers, 2021, 38(9): 2837-2841. | |
32 | ZHANG Z, MA X, MS J. Local differential privacy based membership-privacy-preserving federated learning for deep-learning-driven remote sensing[J]. Remote Sensing, 2023, 15(20): No.5050. |
33 | DUAN Q, HU S, DENG R, et al. Combined federated and split learning in edge computing for ubiquitous intelligence in internet of things: state-of-the-art and future directions[J]. Sensors, 2022, 22(16): No.5983. |
34 | 罗长银,王君宇,陈学斌,等. 改进的联邦加权平均算法[J]. 计算机应用, 2022, 42(4): 1131-1136. |
LUO C Y, WANG J Y, CHEN X B, et al. Improved federated weighted average algorithm[J]. Journal of Computer Applications, 2022, 42(4): 1131-1136. | |
35 | INAN A, GURSOY M E, SAYGIN Y. Sensitivity analysis for non-interactive differential privacy: bounds and efficient algorithms[J]. IEEE Transactions on Dependable and Secure Computing, 2020, 17(1): 194-207. |
36 | 尹春勇,屈锐. 基于个性化差分隐私的联邦学习算法[J]. 计算机应用, 2023, 43(4): 1160-1168. |
YIN C Y, QU Y. Federated learning algorithm based on personalized differential privacy[J]. Journal of Computer Applications, 2023, 43(4): 1160-1168. | |
37 | 张国鹏,陈学斌,王豪石,等. 面向本地差分隐私的K-Prototypes聚类方法[J]. 计算机应用, 2022, 42(12): 3813-3821. |
ZHANG G P, CHEN X B, WANG H S, et al. K-Prototypes clustering method for local differential privacy[J]. Journal of Computer Applications, 2022, 42(12): 3813-3821. | |
38 | DUCHI J C, JORDAN M I, WAINWRIGHT M J. Minimax optimal procedures for locally private estimation[J]. Journal of the American Statistical Association, 2018, 113(521): 182-201. |
39 | WANG N, XIAO X, YANG Y, et al. Collecting and analyzing multidimensional data with local differential privacy[C]// Proceedings of the IEEE 35th International Conference on Data Engineering. Piscataway: IEEE, 2019: 638-649. |
40 | HELBER P, BISCHKE B, DENGEL A, et al. EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(7): 2217-2226. |
41 | 芦国军,陈丽芳. 基于深度卷积神经网络的遥感图像场景分类[J]. 太原师范学院学报(自然科学版), 2019, 18(1):57-62. |
LU G J, CHEN L F. Remote sensing image classification based on deep convolution neural network[J]. Journal of Taiyuan Normal University (Natural Science Edition), 2019, 18(1):57-62. | |
42 | DAI D, YANG W. Satellite image classification via two-layer sparse coding with biased image representation[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(1):173-176. |
43 | DIMITROVSKI I, KITANOVSKI I, KOCEV D, et al. Current trends in deep learning for earth observation: an open-source benchmark arena for image classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 197: 18-35. |
[1] | 任志强, 陈学斌. 基于历史模型更新的自适应防御机制FedAud[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 490-496. |
[2] | 徐超, 张淑芬, 陈海田, 彭璐璐, 张帅华. 基于自适应差分隐私与客户选择优化的联邦学习方法[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 482-489. |
[3] | 张淑芬, 张宏扬, 任志强, 陈学斌. 联邦学习的公平性综述[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 1-14. |
[4] | 朱亮, 慕京哲, 左洪强, 谷晶中, 朱付保. 基于联邦图神经网络的位置隐私保护推荐方案[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 136-143. |
[5] | 晏燕, 钱星颖, 闫鹏斌, 杨杰. 位置大数据的联邦学习统计预测与差分隐私保护方法[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 127-135. |
[6] | 陈廷伟, 张嘉诚, 王俊陆. 面向联邦学习的随机验证区块链构建[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2770-2776. |
[7] | 张治政, 张啸剑, 王俊清, 冯光辉. 结合差分隐私与安全聚集的联邦空间数据发布方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2777-2784. |
[8] | 沈哲远, 杨珂珂, 李京. 基于双流神经网络的个性化联邦学习方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2319-2325. |
[9] | 罗玮, 刘金全, 张铮. 融合秘密分享技术的双重纵向联邦学习框架[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1872-1879. |
[10] | 陈学斌, 任志强, 张宏扬. 联邦学习中的安全威胁与防御措施综述[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1663-1672. |
[11] | 余孙婕, 曾辉, 熊诗雨, 史红周. 基于生成式对抗网络的联邦学习激励机制[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 344-352. |
[12] | 彭鹏, 倪志伟, 朱旭辉, 陈千. 改进萤火虫群算法协同差分隐私的干扰轨迹发布[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 496-503. |
[13] | 张祖篡, 陈学斌, 高瑞, 邹元怀. 基于标签分类的联邦学习客户端选择方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3759-3765. |
[14] | 高瑞, 陈学斌, 张祖篡. 面向部分图更新的动态社交网络隐私发布方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3831-3838. |
[15] | 巫婕, 钱雪忠, 宋威. 基于相似度聚类和正则化的个性化联邦学习[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3345-3353. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||