Intrusion detection method for IoT in heterogeneous environment
In order to address the issue of inadequate training efficiency and subpar model performance encountered by Internet of things (IoT) devices when dealing with resource constraints and non-independent and identically distributed (Non-IID) data, a novel personalized pruning federated learning frame wo...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2024-04-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024087/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539217570660352 |
|---|---|
| author | LIU Jing MU Zelin LAI Yingxu |
| author_facet | LIU Jing MU Zelin LAI Yingxu |
| author_sort | LIU Jing |
| collection | DOAJ |
| description | In order to address the issue of inadequate training efficiency and subpar model performance encountered by Internet of things (IoT) devices when dealing with resource constraints and non-independent and identically distributed (Non-IID) data, a novel personalized pruning federated learning frame work for IoT intrusion detection was put forth. Initially, a channel importance scoring-based structured pruning strategy was proposed, facilitating the generation of sub-models to be disseminated to resource-limited clients, thereby harmonizing model accuracy and complexity. Subsequently, an innovative heterogeneous model aggregation algorithm was introduced, utilizing similarity-weighted coefficients for channel averaging, thereby effectively mitigating the adverse effects of Non-IID data during the model aggregation process. Ultimately, experimental results derived from the network intrusion dataset BoT-IoT substantiate that, relative to existing methods, the proposed method notably curtails the time expenditure of resource-constrained clients, and improves processing speed by 20.82%, while enhancing the accuracy of intrusion detection by 0.86% in Non-IID conditions. |
| format | Article |
| id | doaj-art-99d33240ccd647afa745fbf65233af01 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2024-04-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-99d33240ccd647afa745fbf65233af012025-01-14T07:24:14ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2024-04-014511412759254910Intrusion detection method for IoT in heterogeneous environmentLIU JingMU ZelinLAI YingxuIn order to address the issue of inadequate training efficiency and subpar model performance encountered by Internet of things (IoT) devices when dealing with resource constraints and non-independent and identically distributed (Non-IID) data, a novel personalized pruning federated learning frame work for IoT intrusion detection was put forth. Initially, a channel importance scoring-based structured pruning strategy was proposed, facilitating the generation of sub-models to be disseminated to resource-limited clients, thereby harmonizing model accuracy and complexity. Subsequently, an innovative heterogeneous model aggregation algorithm was introduced, utilizing similarity-weighted coefficients for channel averaging, thereby effectively mitigating the adverse effects of Non-IID data during the model aggregation process. Ultimately, experimental results derived from the network intrusion dataset BoT-IoT substantiate that, relative to existing methods, the proposed method notably curtails the time expenditure of resource-constrained clients, and improves processing speed by 20.82%, while enhancing the accuracy of intrusion detection by 0.86% in Non-IID conditions.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024087/federated learningintrusion detectionmodel pruningNon-IID |
| spellingShingle | LIU Jing MU Zelin LAI Yingxu Intrusion detection method for IoT in heterogeneous environment Tongxin xuebao federated learning intrusion detection model pruning Non-IID |
| title | Intrusion detection method for IoT in heterogeneous environment |
| title_full | Intrusion detection method for IoT in heterogeneous environment |
| title_fullStr | Intrusion detection method for IoT in heterogeneous environment |
| title_full_unstemmed | Intrusion detection method for IoT in heterogeneous environment |
| title_short | Intrusion detection method for IoT in heterogeneous environment |
| title_sort | intrusion detection method for iot in heterogeneous environment |
| topic | federated learning intrusion detection model pruning Non-IID |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024087/ |
| work_keys_str_mv | AT liujing intrusiondetectionmethodforiotinheterogeneousenvironment AT muzelin intrusiondetectionmethodforiotinheterogeneousenvironment AT laiyingxu intrusiondetectionmethodforiotinheterogeneousenvironment |