An Edge-Aware Learning Framework for IoT Malware Classification Using Block-Average-Based Adaptive Dimensionality Reduction
Shohreh Ajoudanian
1
(
1Faculty of Computer Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran,
)
Maryam Nooraei Abadeh
2
(
Department of Computer Engineering, Abadan Branch, Islamic Azad University, Abadan, Iran, ma.nooraei@iau.ac.ir
)
Keywords: Internet of Things, Malware Classification, Machine Learning, Edge Processing, Block Average-Based Dimensionality Reduction,
Abstract :
With the rapid expansion of the Internet of Things (IoT), the number of devices connected to the network has increased significantly, which has created major challenges in cybersecurity and processing a huge amount of data. One of the most important challenges is the detection of new malware that traditional signature-based methods are unable to identify. In this regard, the use of machine learning has been proposed as a new solution for classifying IoT malware, but directly implementing these models on IoT devices faces serious problems due to processing limitations, limited memory, and high energy consumption. In this paper, an edge-aware learning framework for classifying IoT malware is introduced that uses an adaptive block-averaged dimensionality reduction method. This method processes data locally on edge devices, which helps reduce the need to send large amounts of data to cloud servers. As a result, the use of this framework reduces processing latency, increases the speed of response to threats, and improves efficiency in resource-constrained environments. By applying adaptive dimensionality reduction, data features are optimally reduced without losing key information, which not only improves the performance of machine learning models but also reduces energy consumption. Ultimately, this method enables the implementation of high-performance and secure real-time security systems in IoT environments, significantly helping to increase the efficiency of these systems.
[1]
A. N. Almazroi AA, "Deep learning hybridization for improved malware detection in smart Internet of Things.," Sci Rep, 2024. [2] e. a. Alasmary H, "Analyzing and detecting emerging Internet of Things malware: a graph-based approach," IEEE Internet Things J, 2019
. [3] A. M. G. a. K. Grolinger, "Deep Learning: Edge-Cloud Data Analytics for IoT," Department of Electrical and Computer Engineering Western University, 2019
. [4] W. K. Ali I, Bayomi H. , "Dimensionality reduction for images of IoT using machine learning," 2024, doi: 10.1038/s41598-024-57385-4
. . [5] M. D. i. I. S. u. M. L. Techniques, "International Journal of Wireless & Mobile Networks," 2023, doi: 10.5121/ijwmn.2023.15602
. [6]
R. Ghadiri, "Security and Performance Analysis of Edge Computing in IoT," 2023. [7] M. E. Ataei, A.; Shakerian, A.; Landry, R., Jr.; Chevrette, G. , "Publish/Subscribe Method for Real-Time Data Processing in Massive IoT Leveraging Blockchain for Secured Storage," Sensors 2023, doi: https://doi.org/10.3390/s23249692
. [8] C. S. S. Anthony Nduka, "Real-Time Edge Analytics for IoT Networks: Optimizing Data Processing and Decision-Making in Smart Cities " Computer Science, 2024
[9]
L. G. V. Galli A, Moscato V, Postiglione M, Sperlì G. , "Explainability in AI-based behavioral malware detection systems.," Comput Secur, 2024. [10] L. G. Bae SI, Im EG., "Ransomware detection using machine learning algorithms. Concurrency," Comput Pract Exper, vol. 18, no. 32, 2020
. [11] R. C. Brengel M, "Scalable {YARA-based} malware intelligence," in 30th USENIX Security Symposium (USENIX Security 21), pp. 3541–3558, 2021
. [12] S. L. Li J, Yan Q, Li Z, Srisa-An W, Ye H. Li J, Sun L, Yan Q, Li Z, Srisa-An W, Ye H. . "Significant permission identification for machine-learning-based android malware detection," IEEE Trans Ind Inf vol. 14, no. 7, 2018
. [13] Z. Q. Li S, Zhou R, Lv Q. , "Intelligent malware detection based on graph convolutional network. ," J Supercomput, 2022
. [14] S. S. Baptista I, Kolokotronis N, "A novel malware detection system based on machine learning and binary visualization," IEEE International Conference on Communications Workshops (ICC Workshops), 2019
. [15] C. X. Naeem H, Ullah F, Jabbar S, Dong S. , "A deep convolutional neural network stacked ensemble for malware threat classification in internet of things.," J Circuits Syst Comput 2022
. [16] K. S. Zaza AM, Abualsaud K,, "Lightweight iot malware detection solution using cnn classification," in 2020 IEEE 3rd 5G World Forum (5GWF), 2020
. [17] W. J. Yuan B, Wu P, Qing X., "IoT malware classification based on lightweight convolutional neural networks," IEEE Internet Things J vol. 5, no. 9, 2021
. [18] P. J. Jeon J, Jeong Y-S. , "Dynamic analysis for IoT malware detection with convolution neural network model. ," IEEE Access 2020
. [19] T. R. Ghahramani M, Shojafar M, Javidan R, Wan S,, "Deep Image: A precious image based deep learning method for online malware detection in IoT Environment," Internet of Things, 2024
. [20]
K. I. Dong H, "Image-based malware analysis for enhanced IoT security in smart cities.," Internet Things, 2024. [21] V. D. Su J, Prasad S, Sgandurra S, Feng Y, Sakurai K, , "Lightweight classification of IoT malware based on image recognition," 2018 IEEE 42Nd annual computer software and applications conference (COMPSAC), 2018
. [22] C. A. Yang L, Laziuk L, Ahmadzadeh L, Wang G., , "BODMAS: an open dataset for learning based temporal analysis of PE malware," in 2021 IEEE Security and Privacy Workshops (SPW), 2021
. [23] E. M. Kanan T, Maria KA, Alia M., "Exploring the potential of IoT-based learning environments in education.," Int J Adv Soft Comput Appl vol. 3, no. 15, 2023
. [24] K. S. Singh D, "Malware detection in IoT devices using machine learning: a review," presented at the 2024 International Conference on Computational Intelligence and Computing Applications (ICCICA), 2024
. [25] B. A. Sen B, Prakash C, Ammarullah MI. , "Prediction of specific cutting energy consumption in eco-benign lubricating environment for biomedical industry applications: exploring efficacy of GEP, ANN, and RSM models.," AIP Adv, 2024
. [26] N. R. Liu T, Bhatt MW, Shabaz M. , "A study on detection and defence of malicious code under network security over biomedical devices," J Eng 2022,
2022. [27] P. D. f. U. Limin Yang, Arridhana Ciptadi, Blue Hexagon Inc, Ihar Laziuk, Blue Hexagon Inc, Ali Ahmadzadeh, Blue Hexagon Inc, Gang Wang, Associate Professor at UIUC. BODMAS Malware Dataset
.