Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches
The Internet of Things (IoT) has transformed modern technology by interconnecting devices and systems, improving efficiency and functionality across various domains. However, its rapid expansion has also introduced significant security vulnerabilities, necessitating the development of robust intrusi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Insight Society
2025
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/45210/ |
| _version_ | 1848827354629013504 |
|---|---|
| author | Amir Muhammad Hafiz, Othman Mohd Faizal, Ab Razak Ahmad Firdaus, Zainal Abidin Syazwani, Ramli Wan Nur Syamilah, Wan Ali |
| author_facet | Amir Muhammad Hafiz, Othman Mohd Faizal, Ab Razak Ahmad Firdaus, Zainal Abidin Syazwani, Ramli Wan Nur Syamilah, Wan Ali |
| author_sort | Amir Muhammad Hafiz, Othman |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | The Internet of Things (IoT) has transformed modern technology by interconnecting devices and systems, improving efficiency and functionality across various domains. However, its rapid expansion has also introduced significant security vulnerabilities, necessitating the development of robust intrusion detection systems (IDS) to counter evolving cyber threats. Despite advancements in IDS research, particularly through deep learning integration, a systematic bibliometric analysis assessing global research trends, key contributors, and collaboration networks remains lacking. This study addresses that gap by conducting a bibliometric analysis of IDS for IoT using deep learning, focusing on articles published between 2016 and 2024 in the Scopus database. It examines global research trends, keyword co-occurrences, publication patterns, citation dynamics, and international collaborations, offering a comprehensive overview of the field. The findings indicate a significant rise in IDS research, with India, China, the United States, and Saudi Arabia emerging as leading contributors and collaborators. The analysis also highlights influential authors and institutions driving advancements in deep learning for IoT security. Keyword analysis reveals the prominence of terms such as "machine learning," "deep learning," and "intrusion detection," underscoring the field’s focus on artificial intelligence for IoT security. This bibliometric study enhances the understanding of research dynamics in IDS for IoT, identifies gaps for future exploration, and provides valuable insights to drive innovation and global collaboration in this critical area of cybersecurity. |
| first_indexed | 2025-11-15T03:59:23Z |
| format | Article |
| id | ump-45210 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:59:23Z |
| publishDate | 2025 |
| publisher | Insight Society |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-452102025-07-30T06:39:28Z https://umpir.ump.edu.my/id/eprint/45210/ Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches Amir Muhammad Hafiz, Othman Mohd Faizal, Ab Razak Ahmad Firdaus, Zainal Abidin Syazwani, Ramli Wan Nur Syamilah, Wan Ali QA75 Electronic computers. Computer science The Internet of Things (IoT) has transformed modern technology by interconnecting devices and systems, improving efficiency and functionality across various domains. However, its rapid expansion has also introduced significant security vulnerabilities, necessitating the development of robust intrusion detection systems (IDS) to counter evolving cyber threats. Despite advancements in IDS research, particularly through deep learning integration, a systematic bibliometric analysis assessing global research trends, key contributors, and collaboration networks remains lacking. This study addresses that gap by conducting a bibliometric analysis of IDS for IoT using deep learning, focusing on articles published between 2016 and 2024 in the Scopus database. It examines global research trends, keyword co-occurrences, publication patterns, citation dynamics, and international collaborations, offering a comprehensive overview of the field. The findings indicate a significant rise in IDS research, with India, China, the United States, and Saudi Arabia emerging as leading contributors and collaborators. The analysis also highlights influential authors and institutions driving advancements in deep learning for IoT security. Keyword analysis reveals the prominence of terms such as "machine learning," "deep learning," and "intrusion detection," underscoring the field’s focus on artificial intelligence for IoT security. This bibliometric study enhances the understanding of research dynamics in IDS for IoT, identifies gaps for future exploration, and provides valuable insights to drive innovation and global collaboration in this critical area of cybersecurity. Insight Society 2025-06-14 Article PeerReviewed pdf en cc_by_sa_4 https://umpir.ump.edu.my/id/eprint/45210/1/Trends%20in%20IoT%20intrusion%20detection_%20A%20bibliometric%20analysis%20of%20deep%20learning%20approaches.pdf Amir Muhammad Hafiz, Othman and Mohd Faizal, Ab Razak and Ahmad Firdaus, Zainal Abidin and Syazwani, Ramli and Wan Nur Syamilah, Wan Ali (2025) Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches. International Journal on Advanced Science, Engineering and Information Technology, 15 (3). pp. 754 -763. ISSN 2088-5334. (Published) https://doi.org/10.18517/ijaseit.15.3.13022 https://doi.org/10.18517/ijaseit.15.3.13022 https://doi.org/10.18517/ijaseit.15.3.13022 |
| spellingShingle | QA75 Electronic computers. Computer science Amir Muhammad Hafiz, Othman Mohd Faizal, Ab Razak Ahmad Firdaus, Zainal Abidin Syazwani, Ramli Wan Nur Syamilah, Wan Ali Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches |
| title | Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches |
| title_full | Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches |
| title_fullStr | Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches |
| title_full_unstemmed | Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches |
| title_short | Trends in IoT intrusion detection: A bibliometric analysis of deep learning approaches |
| title_sort | trends in iot intrusion detection: a bibliometric analysis of deep learning approaches |
| topic | QA75 Electronic computers. Computer science |
| url | https://umpir.ump.edu.my/id/eprint/45210/ https://umpir.ump.edu.my/id/eprint/45210/ https://umpir.ump.edu.my/id/eprint/45210/ |