A novel lightweight Machine Learning framework for IoT malware classification based on matrix block mean Downsampling
In recent years, the number of smart objects connected through the Internet of Things (IoT) has increased significantly. These smart objects are susceptible to cybersecurity threats and are easily affected by IoT malware. Malwares, if not detected, can harm different components of the IoT: smart obj...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Ain Shams Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090447924005860 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526262830465024 |
|---|---|
| author | Mahmoud E. Farfoura Ibrahim Mashal Ahmad Alkhatib Radwan M. Batyha Didi Rosiyadi |
| author_facet | Mahmoud E. Farfoura Ibrahim Mashal Ahmad Alkhatib Radwan M. Batyha Didi Rosiyadi |
| author_sort | Mahmoud E. Farfoura |
| collection | DOAJ |
| description | In recent years, the number of smart objects connected through the Internet of Things (IoT) has increased significantly. These smart objects are susceptible to cybersecurity threats and are easily affected by IoT malware. Malwares, if not detected, can harm different components of the IoT: smart objects, communication network, and the applications, leading to data theft and privacy breach. Despite that machine learning is incredibly successful at detecting malware, it cannot be deployed in IoT environment due to its computation complexity and high processing resources it demands. This paper proposes a lightweight machine learning framework for real-time IoT malware detection with limited computing burden. The framework is based on novel feature extraction technique; the Matrix Block Mean Downsampling (MBMD), and various machine learning algorithms are implemented. The experiments carried out on BODMAS dataset show the superiority of the proposed approach in detecting IoT malware with an F1-score of more than 99%. |
| format | Article |
| id | doaj-art-3f58911e6cd44f0795e422ee5a4f41e0 |
| institution | Kabale University |
| issn | 2090-4479 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ain Shams Engineering Journal |
| spelling | doaj-art-3f58911e6cd44f0795e422ee5a4f41e02025-01-17T04:49:24ZengElsevierAin Shams Engineering Journal2090-44792025-01-01161103205A novel lightweight Machine Learning framework for IoT malware classification based on matrix block mean DownsamplingMahmoud E. Farfoura0Ibrahim Mashal1Ahmad Alkhatib2Radwan M. Batyha3Didi Rosiyadi4Cybersecurity Department, Al-Zaytoonah University of Jordan, Amman, Jordan; Corresponding author.Cybersecurity Department, Al-Zaytoonah University of Jordan, Amman, JordanCybersecurity Department, Al-Zaytoonah University of Jordan, Amman, JordanFaculty of Information Technology, Applied Science Private University, Amman 11931, JordanNational Research and Innovation Agency, IndonesiaIn recent years, the number of smart objects connected through the Internet of Things (IoT) has increased significantly. These smart objects are susceptible to cybersecurity threats and are easily affected by IoT malware. Malwares, if not detected, can harm different components of the IoT: smart objects, communication network, and the applications, leading to data theft and privacy breach. Despite that machine learning is incredibly successful at detecting malware, it cannot be deployed in IoT environment due to its computation complexity and high processing resources it demands. This paper proposes a lightweight machine learning framework for real-time IoT malware detection with limited computing burden. The framework is based on novel feature extraction technique; the Matrix Block Mean Downsampling (MBMD), and various machine learning algorithms are implemented. The experiments carried out on BODMAS dataset show the superiority of the proposed approach in detecting IoT malware with an F1-score of more than 99%.http://www.sciencedirect.com/science/article/pii/S2090447924005860Internet of ThingsMalwareMachine learningDimensionality reductionRandom forestLogistic regression |
| spellingShingle | Mahmoud E. Farfoura Ibrahim Mashal Ahmad Alkhatib Radwan M. Batyha Didi Rosiyadi A novel lightweight Machine Learning framework for IoT malware classification based on matrix block mean Downsampling Ain Shams Engineering Journal Internet of Things Malware Machine learning Dimensionality reduction Random forest Logistic regression |
| title | A novel lightweight Machine Learning framework for IoT malware classification based on matrix block mean Downsampling |
| title_full | A novel lightweight Machine Learning framework for IoT malware classification based on matrix block mean Downsampling |
| title_fullStr | A novel lightweight Machine Learning framework for IoT malware classification based on matrix block mean Downsampling |
| title_full_unstemmed | A novel lightweight Machine Learning framework for IoT malware classification based on matrix block mean Downsampling |
| title_short | A novel lightweight Machine Learning framework for IoT malware classification based on matrix block mean Downsampling |
| title_sort | novel lightweight machine learning framework for iot malware classification based on matrix block mean downsampling |
| topic | Internet of Things Malware Machine learning Dimensionality reduction Random forest Logistic regression |
| url | http://www.sciencedirect.com/science/article/pii/S2090447924005860 |
| work_keys_str_mv | AT mahmoudefarfoura anovellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT ibrahimmashal anovellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT ahmadalkhatib anovellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT radwanmbatyha anovellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT didirosiyadi anovellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT mahmoudefarfoura novellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT ibrahimmashal novellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT ahmadalkhatib novellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT radwanmbatyha novellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling AT didirosiyadi novellightweightmachinelearningframeworkforiotmalwareclassificationbasedonmatrixblockmeandownsampling |