Explainable Security in SDN-Based IoT Networks
The significant advances in wireless networks in the past decade have made a variety of Internet of Things (IoT) use cases possible, greatly facilitating many operations in our daily lives. IoT is only expected to grow with 5G and beyond networks, which will primarily rely on software-defined networ...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/24/7326 |
| _version_ | 1797544072046444544 |
|---|---|
| author | Alper Kaan Sarica Pelin Angin |
| author_facet | Alper Kaan Sarica Pelin Angin |
| author_sort | Alper Kaan Sarica |
| collection | DOAJ |
| description | The significant advances in wireless networks in the past decade have made a variety of Internet of Things (IoT) use cases possible, greatly facilitating many operations in our daily lives. IoT is only expected to grow with 5G and beyond networks, which will primarily rely on software-defined networking (SDN) and network functions virtualization for achieving the promised quality of service. The prevalence of IoT and the large attack surface that it has created calls for SDN-based intelligent security solutions that achieve real-time, automated intrusion detection and mitigation. In this paper, we propose a real-time intrusion detection and mitigation solution for SDN, which aims to provide autonomous security in the high-traffic IoT networks of the 5G and beyond era, while achieving a high degree of interpretability by human experts. The proposed approach is built upon automated flow feature extraction and classification of flows while using random forest classifiers at the SDN application layer. We present an SDN-specific dataset that we generated for IoT and provide results on the accuracy of intrusion detection in addition to performance results in the presence and absence of our proposed security mechanism. The experimental results demonstrate that the proposed security approach is promising for achieving real-time, highly accurate detection and mitigation of attacks in SDN-managed IoT networks. |
| first_indexed | 2024-03-10T13:54:17Z |
| format | Article |
| id | doaj.art-735c1ea00fab4e678cf72b1d2f53fe49 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T13:54:17Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-735c1ea00fab4e678cf72b1d2f53fe492023-11-21T01:45:31ZengMDPI AGSensors1424-82202020-12-012024732610.3390/s20247326Explainable Security in SDN-Based IoT NetworksAlper Kaan Sarica0Pelin Angin1Department of Computer Engineering, Middle East Technical University, Ankara 06800, TurkeyDepartment of Computer Engineering, Middle East Technical University, Ankara 06800, TurkeyThe significant advances in wireless networks in the past decade have made a variety of Internet of Things (IoT) use cases possible, greatly facilitating many operations in our daily lives. IoT is only expected to grow with 5G and beyond networks, which will primarily rely on software-defined networking (SDN) and network functions virtualization for achieving the promised quality of service. The prevalence of IoT and the large attack surface that it has created calls for SDN-based intelligent security solutions that achieve real-time, automated intrusion detection and mitigation. In this paper, we propose a real-time intrusion detection and mitigation solution for SDN, which aims to provide autonomous security in the high-traffic IoT networks of the 5G and beyond era, while achieving a high degree of interpretability by human experts. The proposed approach is built upon automated flow feature extraction and classification of flows while using random forest classifiers at the SDN application layer. We present an SDN-specific dataset that we generated for IoT and provide results on the accuracy of intrusion detection in addition to performance results in the presence and absence of our proposed security mechanism. The experimental results demonstrate that the proposed security approach is promising for achieving real-time, highly accurate detection and mitigation of attacks in SDN-managed IoT networks.https://www.mdpi.com/1424-8220/20/24/7326SDNsecuritymachine learning5GIoTintrusion detection |
| spellingShingle | Alper Kaan Sarica Pelin Angin Explainable Security in SDN-Based IoT Networks Sensors SDN security machine learning 5G IoT intrusion detection |
| title | Explainable Security in SDN-Based IoT Networks |
| title_full | Explainable Security in SDN-Based IoT Networks |
| title_fullStr | Explainable Security in SDN-Based IoT Networks |
| title_full_unstemmed | Explainable Security in SDN-Based IoT Networks |
| title_short | Explainable Security in SDN-Based IoT Networks |
| title_sort | explainable security in sdn based iot networks |
| topic | SDN security machine learning 5G IoT intrusion detection |
| url | https://www.mdpi.com/1424-8220/20/24/7326 |
| work_keys_str_mv | AT alperkaansarica explainablesecurityinsdnbasediotnetworks AT pelinangin explainablesecurityinsdnbasediotnetworks |