Deep Learning Approach for IoT Malware Detection and Classification based on Squirrel Search Algorithm and Convolutional Neural Network (IMD_SSACNN)

Deep Learning Approach for IoT Malware Detection and Classification based on Squirrel Search Algorithm and Convolutional Neural Network (IMD_SSACNN)
  IJETT-book-cover           
  
© 2024 by IJETT Journal
Volume-72 Issue-10
Year of Publication : 2024
Author : V. S. Jeyalakshmi, Krishnan Nallaperumal
DOI : 10.14445/22315381/IJETT-V72I10P128

How to Cite?
V. S. Jeyalakshmi, Krishnan Nallaperumal,"Deep Learning Approach for IoT Malware Detection and Classification based on Squirrel Search Algorithm and Convolutional Neural Network (IMD_SSACNN)," International Journal of Engineering Trends and Technology, vol. 72, no. 10, pp. 306-315, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I10P128

Abstract
The number of Internet of Things (IoT) devices that are exposed to the public has been rising as more of these devices are connecting to the internet using their default settings. Due to the variety of designs and the IoT's limited computation and storage capacities, it is challenging to implement sufficient security measures, which makes it more susceptible to infection. Accurate IoT malware identification and family attribution are crucial in order to begin implementing attack mitigation/prevention tactics, which is why they are so important in order to reduce the threat. To prevent the risks caused by malicious code, various research has been done on the identification of IoT malware. It might be challenging to recognize the novel variant IoT virus that is being created rapidly, even though existing models might successfully identify hazardous IoT code found through static analysis. This research introduced a novel IoT Malware Detection with a Squirrel Search Algorithm and Convolutional Neural Network (IMD-SSACNN). IoT malware datasets are used to conduct an exhaustive analysis of the suggested technique. IMD-SSACNN is able to lessen the damage that malware infestation brings to IoT devices by examining and analyzing the massive volume of behavior data generated by dynamic analysis. The experimental findings show that the suggested IMD-SSACNN is the preferred approach since it has a greater detection rate than the earlier malware detection algorithms.

Keywords
Deep Learning, Malware detection, IoT malware, Mitigation, Convolution neural network.

References

[1] Lionel Sujay Vailshery, Number of Internet of Things (IoT) Connections Worldwide from 2022 to 2023, with Forecasts from 2024 to 2033, Statista, 2024. [Online]. Available: https://www.statista.com/statistics/802690/ worldwide-connected-devices-by-access-technology/
[2] Zhiwei Guo et al., “Robust Spammer Detection Using Collaborative Neural Network in Internet-of-Things Applications,” IEEE Internet of Things Journal, vol. 8, no. 12, pp. 9549-9558, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] New IoT-Malware Grew Three-Fold in H1 2018, Kaspersky, 2018. [Online]. Available: https://www.kaspersky.com/about/press-releases/new-iot-malware-grew-three-fold-in-h1-2018
[4] Baoguo Yuan et al., “IoT Malware Classification Based on Lightweight Convolutional Neural Networks,” IEEE Internet of Things Journal, vol. 9, no. 5, pp. 3770-3783, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Danish Vasan et al., “IMCFN: Image-Based Malware Classification Using Fine-Tuned Convolutional Neural Network Architecture,” Computer Networks, vol. 171, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Daniel Gibert, Carles Mateu, and Jordi Planes, “HYDRA: A Multimodal Deep Learning Framework for Malware Classification,” Computers & Security, vol. 95, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Jueun Jeon, Jong Hyuk Park, and Young-Sik Jeong, “Dynamic Analysis for IoT Malware Detection with Convolution Neural Network Model,” IEEE Access, vol. 8, pp. 96899-96911, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Danish Vasan et al., “Image-Based Malware Classification Using Ensemble of CNN Architectures (IMCEC),” Computers & Security, vol. 92, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Seungho Jeon, and Jongsub Moon, “Malware-Detection Method with a Convolutional Recurrent Neural Network Using Opcode Sequences,” Information Sciences, vol. 535, pp. 1-15, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Yifei Jian et al., “A Novel Framework for Image-Based Malware Detection with a Deep Neural Network,” Computers & Security, vol. 109, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Giacomo Iadarola et al., “Towards an Interpretable Deep Learning Model for Mobile Malware Detection and Family Identification,” Computers & Security, vol. 105, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Qikai Lu et al., “Self-Attentive Models for Real-Time Malware Classification,” IEEE Access, vol. 10, pp. 95970-95985, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Zixiao Kong et al., “MalFSM: Feature Subset Selection Method for Malware Family Classification,” Chinese Journal of Electronics, vol. 32, no. 1, pp. 26-38, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Microsoft Malware Classification Challenge (BIG 2015), Kaggle, 2015. [Online]. Available: https://www.kaggle.com/c/malware-classification/
[15] Nadia Daoudi et al., “DexRay: A Simple, Yet Effective Deep Learning Approach to Android Malware Detection Based on Image Representation of Bytecode,” Second International Workshop: Deployable Machine Learning for Security Defense, pp. 81-106, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[16] V.N. Ganapathi Raju et al., “Study the Influence of Normalization/Transformation Process on the Accuracy of Supervised Classification,” 2020 Third International Conference on Smart Systems and Inventive Technology, Tirunelveli, India, pp. 729-735, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Mohit Jain, Vijander Singh, and Asha Rani, “A Novel Nature-Inspired Algorithm for Optimization: Squirrel Search Algorithm,” Swarm and Evolutionary Computation, vol. 44, pp. 148-175, 2019.
[CrossRef] [Google Scholar] [Publisher Link]