Malware Detection Using Tlenet On Image Data
Main Article Content
Abstract
The prevalence of malicious software is referred to as malware and has seen a notable increase today. It is a significant threat to the overall integrity of internet security in modern time is significant. Malware is a dangerous threat to the whole internet users due to its unauthorized data acquisition and inflict damage upon computer systems. Malware detection has gathered a significant attention within academic fields due to the growing prevalence of malware. Threats pose risks to the individual computer users, corporations and governmental entities, etc., to detect the unidentified malware in real-time is difficult. The malware detection systems depend on the examination of the malware signatures and behavioral patterns is by the combination of dynamic and static analysis. The problem is to identify and categorise the malicious software by image analysis techniques. Deep learning (DL) are used for image recognition after the conversion of executable files into image formats in the mailimg and ImageNet datasets. Transfer learning is used to train deep learning models for large-scale datasets. The problem within this method is slow and laborious. In pursuit of the objective, the study investigates the implementation of deep convolutional neural networks to classify the malware. Additionally, it provides methodologies for effectively using transfer learning techniques to compromise the challenges associated with detecting and categorizing the different types of malware. To enhance the classification of malware, a pre-trained convolutional neural network (CNN) in transfer learning is used to categorize the malware images from the Malimg and ImageNet datasets are proposed. The Malimg dataset consists of malicious programs in the form of images are classified using the portable executable files. EfficientNet3 classifier has scored an impressive accuracy of 99.60 percentage.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
McAfee: McAfee Labs Threats Report 2020. https://www.mcafee.com/enterprise/en-us/assets/reports/rp-quarterly-threats-nov 2020.pdf; 2020
Schrittwieser, S., Katzenbeisser, S., Kinder, J., Merzdovnik, G., Weippl, E.: Protecting software through obfuscation: Can it keep pace with progress in code analysis? ACM Comput. Surv. (CSUR) 49(1), 1–37; 2016.
Collberg, C., Thomborson, C., Low, D.: A taxonomy of obfuscating transformations; 1997.
Andriesse, D., Chen, X., Van Der Veen, V., Slowinska, A., Bos, H.: An in-depth analysis of disassembly on full-scale x86/x64 binaries. In: 25th USENIX Security Symposium (USENIX Security 16), pp. 583–600; 2016.
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 60; 2019.
Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.0462; 2017.
Marastoni, N., Giacobazzi, R., Dalla Preda, M.: A deep learning approach to program similarity. In: Proceedings of the 1st International Workshop on Machine Learning and Software Engineering in Symbiosis, pp. 26–35; 2018.
F. Shah, Y. Liu, A. Anwar et al., “Machine learning: the backbone of intelligent trade credit-based systems,” Security and Communication Networks, vol. 2022, Article ID 7149902, 10 pages; 2022.
S. S. Ullah, S. Hussain, A. Gumaei, and H. AlSalman, “A secure NDN framework for Internet of Things enabled healthcare,” Computers, Materials & Continua, vol. 67, no. 1, pp. 223– 240; 2021.
S. Hussain, S. S. Ullah, M. Uddin, J. Iqbal, and C. L. Chen, “A comprehensive survey on signcryption security mechanisms in wireless body area networks,” Sensors, vol. 22, no. 3, p. 1072; 2022.
S. Hussain, S. S. Ullah, I. Ali, J. Xie, and V. N. Inukollu, “Certificateless signature schemes in Industrial Internet of Things: a comparative survey,” Computer Communications, vol. 181, pp. 116–131; 2022.
J. Iqbal, M. Adnan, Y. Khan et al., “Designing a healthcare enabled software-defined wireless body area network architecture for secure medical data and efficient diagnosis,” Journal of Healthcare Engineering, vol. 2022, Article ID 9210761, 19 pages; 2022.
A. S. Parihar, S. Kumar, and S. Khosla, “S-DCNN: stacked deep convolutional neural networks for malware classification,” Multimedia Tools and Applications, vol. 81, no. 21, pp. 30997–31015; 2022.
L. Nataraj, V. Yegneswaran, and P. Porras, “A comparative assessment of malware classification using binary texture analysis and dynamic analysis categories and subject descriptors,” 4th ACM Workshop on Security and Artificial Intelligence; 2011.
ImageNetMarch 2022, https://image-net.org/.
S. Miyawaki, E. A. Hoffman, and C. L. Lin, “Effect of static vs. dynamic imaging on particle transport in CT-based numerical models of human central airways,” Journal of aerosol science, vol. 100, pp. 129–139; 2016.
A. Çayır, U. Ünal, and H. Dağ,“Random CapsNet forest model for imbalanced malware type classification task,” Computers & Security, vol. 102, p. 102133; 2021.
K. Kosmidis and C. Kalloniatis, “Machine learning and images for malware detection and classification,” [Proceedings of the 21st Pan-Hellenic Conference on Informatics, Larissa, Greece]; 2017.
L. Nataraj, S. Karthikeyan, G. Jacob, and B. S. Manjunath, “Malware images: visualization and automatic classification,” [Proceedings of the 8th international symposium on visualization for cyber security, Pittsburgh, Pennsylvania, USA]; 2011.
A. Torralba, K. P. Murphy, W. T. Freeman, and M. A. Rubin, “Context-based vision system for place and object recognition,” [Proceedings Ninth IEEE International Conference on Computer Vision, Nice, France]; 2003.
A. Makandar and A. Patrot, “Malware class recognition using image processing techniques,” [International Conference on Data Management, Analytics and Innovation (ICDMAI), pp. 76–80, Pune, India]; 2017.
L. Alzubaidi, J. Zhang, A. J. Humaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” Journal of big Data, vol. 8, no. 1, pp. 1–74; 2021.
Z. Cui, F. Xue, X. Cai, C. Yang, G.-g. Wang, and J. Chen, “Detection of malicious code variants based on deep learning,” [IEEE Transactions on Industrial Informatics, vol. 14, no. 7, pp. 3187–3196]; 2018.
R. Ronen, M. Radu, C. Feuerstein, E. Yom-Tov, and M. Ahmadi, “Microsoft malware classification challenge,” [https://arxiv.org/abs/1802.10135]; 2018.
W.-C. Lin and Y.-R. Yeh, “Efficient malware classification by binary sequences with one-dimensional convolutional neural networks,” Mathematics, vol. 10, no. 4, p. 608; 2022.
A. Bensaoud, N. Abudawaood, and J. Kalita, “Classifying malware images with convolutional neural network models,” International Journal of Network Security, vol. 22, no. 6, pp. 1022–1031; 2020.
L. Alzubaidi, O. al-Shamma, M. A. Fadhel, L. Farhan, J. Zhang, and Y. Duan, “Optimizing the performance of breast cancer classification by employing the same domain transfer learning from hybrid deep convolutional neural network model,” [Electronics, vol. 9, no. 3, p. 445]; 2020.
M. Tan and Q. Le, “Efficientnet: rethinking model scaling for convolutional neural networks,” [International conference on machine learning, Long Beach, California]; 2019.