A privacy budget adaptive optimization scheme for federated computing power Internet of things
Federated computing power Internet of things (IoT) is designed to deeply integrate computing power with IoT resources, facilitating the efficient utilization of vast and ubiquitously dispersed IoT data and heterogeneous resources through federated learning. Faced with the threats of emerging privacy...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
China InfoCom Media Group
2024-12-01
|
| Series: | 物联网学报 |
| Subjects: | |
| Online Access: | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00440/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586314437885952 |
|---|---|
| author | MA Wenyu CHEN Qian HU Yuxiang YAN Haonan HU Tao YI Peng |
| author_facet | MA Wenyu CHEN Qian HU Yuxiang YAN Haonan HU Tao YI Peng |
| author_sort | MA Wenyu |
| collection | DOAJ |
| description | Federated computing power Internet of things (IoT) is designed to deeply integrate computing power with IoT resources, facilitating the efficient utilization of vast and ubiquitously dispersed IoT data and heterogeneous resources through federated learning. Faced with the threats of emerging privacy attacks, e.g., model inversion attacks and gradient leakage attacks, the academic and industrial communities have widely investigated and applied differential privacy (DP) as an effective privacy protection technique. However, two severe challenges have not been taken into account in the existing DP budget settings, i.e., data heterogeneity issue of local computing power nodes and the fairness of privacy budget allocation, which lead to a significant loss in model accuracy. Therefore, an adaptive optimization scheme for privacy budget was proposed in federated computing power IoT, which was called federated learning based on Cramér-Rao lower bound differential privacy (FedCDP). In specific, to adaptively adjust privacy budgets, the privacy budget estimates for edge computing power nodes based on the Cramér-Rao lower bound theory were analyzed. Furthermore, by assessing the similarity between the local model and the aggregated model, as well as their respective privacy budget proportions, the global contribution of each node was determined, which was used to fairly, also in real time, optimize and adjust the privacy budget settings in conjunction with the estimated privacy budget. Through rigorous theoretical analysis, FedCDP achieves <italic>ε</italic>-DP for local models, and ensures the convergence of the global model. Experimental results on multiple public datasets show that the proposed scheme improves the accuracy of the global model by up to 10.19% under the premise of satisfying the same privacy protection requirements. |
| format | Article |
| id | doaj-art-1043db1be27249c88a8b3012f9453b25 |
| institution | Kabale University |
| issn | 2096-3750 |
| language | zho |
| publishDate | 2024-12-01 |
| publisher | China InfoCom Media Group |
| record_format | Article |
| series | 物联网学报 |
| spelling | doaj-art-1043db1be27249c88a8b3012f9453b252025-01-25T19:00:27ZzhoChina InfoCom Media Group物联网学报2096-37502024-12-018546979606322A privacy budget adaptive optimization scheme for federated computing power Internet of thingsMA WenyuCHEN QianHU YuxiangYAN HaonanHU TaoYI PengFederated computing power Internet of things (IoT) is designed to deeply integrate computing power with IoT resources, facilitating the efficient utilization of vast and ubiquitously dispersed IoT data and heterogeneous resources through federated learning. Faced with the threats of emerging privacy attacks, e.g., model inversion attacks and gradient leakage attacks, the academic and industrial communities have widely investigated and applied differential privacy (DP) as an effective privacy protection technique. However, two severe challenges have not been taken into account in the existing DP budget settings, i.e., data heterogeneity issue of local computing power nodes and the fairness of privacy budget allocation, which lead to a significant loss in model accuracy. Therefore, an adaptive optimization scheme for privacy budget was proposed in federated computing power IoT, which was called federated learning based on Cramér-Rao lower bound differential privacy (FedCDP). In specific, to adaptively adjust privacy budgets, the privacy budget estimates for edge computing power nodes based on the Cramér-Rao lower bound theory were analyzed. Furthermore, by assessing the similarity between the local model and the aggregated model, as well as their respective privacy budget proportions, the global contribution of each node was determined, which was used to fairly, also in real time, optimize and adjust the privacy budget settings in conjunction with the estimated privacy budget. Through rigorous theoretical analysis, FedCDP achieves <italic>ε</italic>-DP for local models, and ensures the convergence of the global model. Experimental results on multiple public datasets show that the proposed scheme improves the accuracy of the global model by up to 10.19% under the premise of satisfying the same privacy protection requirements.http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00440/federated computing power IoTdifferential privacyprivacy budgetadaptive optimization |
| spellingShingle | MA Wenyu CHEN Qian HU Yuxiang YAN Haonan HU Tao YI Peng A privacy budget adaptive optimization scheme for federated computing power Internet of things 物联网学报 federated computing power IoT differential privacy privacy budget adaptive optimization |
| title | A privacy budget adaptive optimization scheme for federated computing power Internet of things |
| title_full | A privacy budget adaptive optimization scheme for federated computing power Internet of things |
| title_fullStr | A privacy budget adaptive optimization scheme for federated computing power Internet of things |
| title_full_unstemmed | A privacy budget adaptive optimization scheme for federated computing power Internet of things |
| title_short | A privacy budget adaptive optimization scheme for federated computing power Internet of things |
| title_sort | privacy budget adaptive optimization scheme for federated computing power internet of things |
| topic | federated computing power IoT differential privacy privacy budget adaptive optimization |
| url | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00440/ |
| work_keys_str_mv | AT mawenyu aprivacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT chenqian aprivacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT huyuxiang aprivacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT yanhaonan aprivacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT hutao aprivacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT yipeng aprivacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT mawenyu privacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT chenqian privacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT huyuxiang privacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT yanhaonan privacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT hutao privacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings AT yipeng privacybudgetadaptiveoptimizationschemeforfederatedcomputingpowerinternetofthings |