IoT Device Identification Using Unsupervised Machine Learning
Device identification is a fundamental issue in the Internet of Things (IoT). Many critical services, including access control and intrusion prevention, are built on correctly identifying each unique device in a network. However, device identification faces many challenges in the IoT. For example, a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/6/320 |
| _version_ | 1797594202391969792 |
|---|---|
| author | Carson Koball Bhaskar P. Rimal Yong Wang Tyler Salmen Connor Ford |
| author_facet | Carson Koball Bhaskar P. Rimal Yong Wang Tyler Salmen Connor Ford |
| author_sort | Carson Koball |
| collection | DOAJ |
| description | Device identification is a fundamental issue in the Internet of Things (IoT). Many critical services, including access control and intrusion prevention, are built on correctly identifying each unique device in a network. However, device identification faces many challenges in the IoT. For example, a common technique to identify a device in a network is using the device’s MAC address. However, MAC addresses can be easily spoofed. On the other hand, IoT devices also include dynamic characteristics such as traffic patterns which could be used for device identification. Machine-learning-assisted approaches are promising for device identification since they can capture dynamic device behaviors and have automation capabilities. Supervised machine-learning-assisted techniques demonstrate high accuracies for device identification. However, they require a large number of labeled datasets, which can be a challenge. On the other hand, unsupervised machine learning can also reach good accuracies without requiring labeled datasets. This paper presents an unsupervised machine-learning approach for IoT device identification. |
| first_indexed | 2024-03-11T02:20:19Z |
| format | Article |
| id | doaj.art-54d1c98f1aaa41a9b16e8c98f9eb7536 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T02:20:19Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-54d1c98f1aaa41a9b16e8c98f9eb75362023-11-18T10:54:28ZengMDPI AGInformation2078-24892023-05-0114632010.3390/info14060320IoT Device Identification Using Unsupervised Machine LearningCarson Koball0Bhaskar P. Rimal1Yong Wang2Tyler Salmen3Connor Ford4The Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD 57042, USAThe Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD 57042, USAThe Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD 57042, USAThe Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD 57042, USAThe Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD 57042, USADevice identification is a fundamental issue in the Internet of Things (IoT). Many critical services, including access control and intrusion prevention, are built on correctly identifying each unique device in a network. However, device identification faces many challenges in the IoT. For example, a common technique to identify a device in a network is using the device’s MAC address. However, MAC addresses can be easily spoofed. On the other hand, IoT devices also include dynamic characteristics such as traffic patterns which could be used for device identification. Machine-learning-assisted approaches are promising for device identification since they can capture dynamic device behaviors and have automation capabilities. Supervised machine-learning-assisted techniques demonstrate high accuracies for device identification. However, they require a large number of labeled datasets, which can be a challenge. On the other hand, unsupervised machine learning can also reach good accuracies without requiring labeled datasets. This paper presents an unsupervised machine-learning approach for IoT device identification.https://www.mdpi.com/2078-2489/14/6/320internet of thingsdevice identificationmachine learningunsupervised machine learning |
| spellingShingle | Carson Koball Bhaskar P. Rimal Yong Wang Tyler Salmen Connor Ford IoT Device Identification Using Unsupervised Machine Learning Information internet of things device identification machine learning unsupervised machine learning |
| title | IoT Device Identification Using Unsupervised Machine Learning |
| title_full | IoT Device Identification Using Unsupervised Machine Learning |
| title_fullStr | IoT Device Identification Using Unsupervised Machine Learning |
| title_full_unstemmed | IoT Device Identification Using Unsupervised Machine Learning |
| title_short | IoT Device Identification Using Unsupervised Machine Learning |
| title_sort | iot device identification using unsupervised machine learning |
| topic | internet of things device identification machine learning unsupervised machine learning |
| url | https://www.mdpi.com/2078-2489/14/6/320 |
| work_keys_str_mv | AT carsonkoball iotdeviceidentificationusingunsupervisedmachinelearning AT bhaskarprimal iotdeviceidentificationusingunsupervisedmachinelearning AT yongwang iotdeviceidentificationusingunsupervisedmachinelearning AT tylersalmen iotdeviceidentificationusingunsupervisedmachinelearning AT connorford iotdeviceidentificationusingunsupervisedmachinelearning |