Research on asynchronous robust federated learning method in vehicle computing power network
The synchronous training mechanism of traditional federated learning was not suitable for dynamic vehicle computing power network scenarios, and lacked effective detection mechanisms under the threat of malicious vehicle attacks. To address the above issues, an asynchronous robust federated learning...
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.2096-3750.2024.00452/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586368294846464 |
|---|---|
| author | YIN Hongbo WANG Shuai ZHANG Ke ZHANG Yin |
| author_facet | YIN Hongbo WANG Shuai ZHANG Ke ZHANG Yin |
| author_sort | YIN Hongbo |
| collection | DOAJ |
| description | The synchronous training mechanism of traditional federated learning was not suitable for dynamic vehicle computing power network scenarios, and lacked effective detection mechanisms under the threat of malicious vehicle attacks. To address the above issues, an asynchronous robust federated learning method was proposed, which achieves vehicle data privacy protection while improving the efficiency of model collaborative training through asynchronous execution of federated learning processes between vehicles. Secondly, a model selection method was designed, and potential malicious model detection and vehicle reputation evaluation methods are proposed to further enhance the robustness of the system. Then, the safety of the proposed method was analyzed in detail from a probabilistic perspective, providing a theoretical basis for optimizing various parameters. Finally, the simulation results show that this method can achieve efficient asynchronous federated learning while having good robustness. |
| format | Article |
| id | doaj-art-c47e60d3898c43dd811573ba2dd4cfad |
| 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-c47e60d3898c43dd811573ba2dd4cfad2025-01-25T19:00:30ZzhoChina InfoCom Media Group物联网学报2096-37502024-12-018142279606465Research on asynchronous robust federated learning method in vehicle computing power networkYIN HongboWANG ShuaiZHANG KeZHANG YinThe synchronous training mechanism of traditional federated learning was not suitable for dynamic vehicle computing power network scenarios, and lacked effective detection mechanisms under the threat of malicious vehicle attacks. To address the above issues, an asynchronous robust federated learning method was proposed, which achieves vehicle data privacy protection while improving the efficiency of model collaborative training through asynchronous execution of federated learning processes between vehicles. Secondly, a model selection method was designed, and potential malicious model detection and vehicle reputation evaluation methods are proposed to further enhance the robustness of the system. Then, the safety of the proposed method was analyzed in detail from a probabilistic perspective, providing a theoretical basis for optimizing various parameters. Finally, the simulation results show that this method can achieve efficient asynchronous federated learning while having good robustness.http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00452/vehicle computing power networkfederated learningrobustnessasynchronous learning |
| spellingShingle | YIN Hongbo WANG Shuai ZHANG Ke ZHANG Yin Research on asynchronous robust federated learning method in vehicle computing power network 物联网学报 vehicle computing power network federated learning robustness asynchronous learning |
| title | Research on asynchronous robust federated learning method in vehicle computing power network |
| title_full | Research on asynchronous robust federated learning method in vehicle computing power network |
| title_fullStr | Research on asynchronous robust federated learning method in vehicle computing power network |
| title_full_unstemmed | Research on asynchronous robust federated learning method in vehicle computing power network |
| title_short | Research on asynchronous robust federated learning method in vehicle computing power network |
| title_sort | research on asynchronous robust federated learning method in vehicle computing power network |
| topic | vehicle computing power network federated learning robustness asynchronous learning |
| url | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00452/ |
| work_keys_str_mv | AT yinhongbo researchonasynchronousrobustfederatedlearningmethodinvehiclecomputingpowernetwork AT wangshuai researchonasynchronousrobustfederatedlearningmethodinvehiclecomputingpowernetwork AT zhangke researchonasynchronousrobustfederatedlearningmethodinvehiclecomputingpowernetwork AT zhangyin researchonasynchronousrobustfederatedlearningmethodinvehiclecomputingpowernetwork |