Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research Direction
With the ongoing efforts for widespread Internet of Things (IoT) adoption, one of the key factors hindering the wide acceptance of IoT is security. Securing IoT networks such as the electric power grid or water supply systems has emerged as a major national and global priority. To address the securi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/15/5122 |
| _version_ | 1797525093683822592 |
|---|---|
| author | Kazi Istiaque Ahmed Mohammad Tahir Mohamed Hadi Habaebi Sian Lun Lau Abdul Ahad |
| author_facet | Kazi Istiaque Ahmed Mohammad Tahir Mohamed Hadi Habaebi Sian Lun Lau Abdul Ahad |
| author_sort | Kazi Istiaque Ahmed |
| collection | DOAJ |
| description | With the ongoing efforts for widespread Internet of Things (IoT) adoption, one of the key factors hindering the wide acceptance of IoT is security. Securing IoT networks such as the electric power grid or water supply systems has emerged as a major national and global priority. To address the security issue of IoT, several studies are being carried out that involve the use of, but are not limited to, blockchain, artificial intelligence, and edge/fog computing. Authentication and authorization are crucial aspects of the CIA triad to protect the network from malicious parties. However, existing authorization and authentication schemes are not sufficient for handling security, due to the scale of the IoT networks and the resource-constrained nature of devices. In order to overcome challenges due to various constraints of IoT networks, there is a significant interest in using machine learning techniques to assist in the authentication and authorization process for IoT. In this paper, recent advances in authentication and authorization techniques for IoT networks are reviewed. Based on the review, we present a taxonomy of authentication and authorization schemes in IoT focusing on machine learning-based schemes. Using the presented taxonomy, a thorough analysis is provided of the authentication and authorization (AA) security threats and challenges for IoT. Furthermore, various criteria to achieve a high degree of AA resiliency in IoT implementations to enhance IoT security are evaluated. Lastly, a detailed discussion on open issues, challenges, and future research directions is presented for enabling secure communication among IoT nodes. |
| first_indexed | 2024-03-10T09:08:52Z |
| format | Article |
| id | doaj.art-1db0e32218cf46f4b3de56a3ce8f74f4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:08:52Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1db0e32218cf46f4b3de56a3ce8f74f42023-11-22T06:10:49ZengMDPI AGSensors1424-82202021-07-012115512210.3390/s21155122Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research DirectionKazi Istiaque Ahmed0Mohammad Tahir1Mohamed Hadi Habaebi2Sian Lun Lau3Abdul Ahad4Department of Computing and Information Systems, Sunway University, Petaling Jaya 47500, Selangor, MalaysiaDepartment of Computing and Information Systems, Sunway University, Petaling Jaya 47500, Selangor, MalaysiaIoT & Wireless Communication Protocols Lab, Department of Electrical and Computer Engineering, International Islamic University Malaysia, Jalan Gombak 53100, Selangor, MalaysiaDepartment of Computing and Information Systems, Sunway University, Petaling Jaya 47500, Selangor, MalaysiaDepartment of Computing and Information Systems, Sunway University, Petaling Jaya 47500, Selangor, MalaysiaWith the ongoing efforts for widespread Internet of Things (IoT) adoption, one of the key factors hindering the wide acceptance of IoT is security. Securing IoT networks such as the electric power grid or water supply systems has emerged as a major national and global priority. To address the security issue of IoT, several studies are being carried out that involve the use of, but are not limited to, blockchain, artificial intelligence, and edge/fog computing. Authentication and authorization are crucial aspects of the CIA triad to protect the network from malicious parties. However, existing authorization and authentication schemes are not sufficient for handling security, due to the scale of the IoT networks and the resource-constrained nature of devices. In order to overcome challenges due to various constraints of IoT networks, there is a significant interest in using machine learning techniques to assist in the authentication and authorization process for IoT. In this paper, recent advances in authentication and authorization techniques for IoT networks are reviewed. Based on the review, we present a taxonomy of authentication and authorization schemes in IoT focusing on machine learning-based schemes. Using the presented taxonomy, a thorough analysis is provided of the authentication and authorization (AA) security threats and challenges for IoT. Furthermore, various criteria to achieve a high degree of AA resiliency in IoT implementations to enhance IoT security are evaluated. Lastly, a detailed discussion on open issues, challenges, and future research directions is presented for enabling secure communication among IoT nodes.https://www.mdpi.com/1424-8220/21/15/5122Internet of ThingsIoTsecurityauthenticationauthorizationmachine learning |
| spellingShingle | Kazi Istiaque Ahmed Mohammad Tahir Mohamed Hadi Habaebi Sian Lun Lau Abdul Ahad Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research Direction Sensors Internet of Things IoT security authentication authorization machine learning |
| title | Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research Direction |
| title_full | Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research Direction |
| title_fullStr | Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research Direction |
| title_full_unstemmed | Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research Direction |
| title_short | Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research Direction |
| title_sort | machine learning for authentication and authorization in iot taxonomy challenges and future research direction |
| topic | Internet of Things IoT security authentication authorization machine learning |
| url | https://www.mdpi.com/1424-8220/21/15/5122 |
| work_keys_str_mv | AT kaziistiaqueahmed machinelearningforauthenticationandauthorizationiniottaxonomychallengesandfutureresearchdirection AT mohammadtahir machinelearningforauthenticationandauthorizationiniottaxonomychallengesandfutureresearchdirection AT mohamedhadihabaebi machinelearningforauthenticationandauthorizationiniottaxonomychallengesandfutureresearchdirection AT sianlunlau machinelearningforauthenticationandauthorizationiniottaxonomychallengesandfutureresearchdirection AT abdulahad machinelearningforauthenticationandauthorizationiniottaxonomychallengesandfutureresearchdirection |