Email: info@ijps.in | Mob: +91-9555269393

Submit Manuscript

Abstract

Design of AI based Malware Detection Technique: A Revolutionized Machine Learning Methodology

Yasir Mahmood Younus

Department of Computer Techniques Engineering, Imam Al-Kadhum College (IKC), Baghdad, Iraq

1 - 10
Vol.19, Jan-Jun, 2025
Receiving Date: 2024-11-15
Acceptance Date: 2024-12-31
Publication Date: 2024-01-03
Download PDF

http://doi.org/10.37648/ijps.v19i01.001

Abstract

This research aims at analyzing the performance of the SVM methodology in the detection of malware by examining cross-traffic in the network using the CICIDS 2017 dataset. First, the raw network traffic data is gathered and then feature extraction, where they compute different attributes such as packets size, duration and protocol of the flow. Normalization is applied to the feature values and dealing with categorical variables is performed as well. Subsequently, a support vector machine (SVM) classifier is learned based on the labeled set of data and an RBF kernel to overcome the problem of the nonlinearity of the separation between benign and malicious traffics. At first the message is scored with some of the measures like accuracy, precision, recall and F1-score and a confusion matrix is used for evaluating the classification. The study also shows that hyperparameter tuning is also a key consideration in enhancing the performance of SVM model. Using grid search, the best values of the regularization parameter CC and kernel parameter γgamma are obtained, and the model attains the highest accuracy of classification and F1-score. For an SVM tuned, the results are as follows: the accuracy is increased to 94%, the F-score is 94% – this illustrates the high efficiency of a tuned model to detect malicious traffic. This work demonstrates where SVM can be used in a network traffic analysis and underpins the importance of feature extraction, data pre-processing, and model fine-tuning in the malware classification process.


Keywords: AI Malware; Cybersecurity; Machine Learning; SVM and Radial Basis Function


References
  1. Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001). Estimating the Support of a High-Dimensional Distribution. Neural Computation, 13(7), 1443–1471.
  2. Nguyen, T. T., Huynh, T. K., & Le, H. H. (2018). Malware Detection Using Network Traffic Classification Based on Support Vector Machines. Journal of Network and Computer Applications, 118, 23-31.
  3. Iglewicz, L., Guss, B., & Veeramachaneni, K. (2020). Detection of Cyber Attacks Using Support Vector Machines. Proceedings of the IEEE International Conference on Computer Science and Information Technology, 1-6.
  4. Ahmed, Amjed Abbas, et al. 'Optimization Technique for Deep Learning Methodology on Power Side Channel Attacks.' 2023 33rd International Telecommunication Networks and Applications Conference. IEEE, 2023.
  5. Zhao, H., & Zhang, M. (2016). Feature Selection for Malware Detection in Network Traffic Based on Mutual Information. Proceedings of the International Conference on Network and System Security, 109- 118.
  6. Ahmed, Amjed Abbas, et al. 'Secure AI for 6G Mobile Devices: Deep Learning Optimization Against Side-Channel Attacks.' IEEE Transactions on Consumer Electronics (2024).
  7. Vaza, Rahul N., Amit B. Parmar, Pankaj S. Mishra, Ibrahim Abdullah, and C. M. Velu. 'Security And Privacy Concerns In AI-Enabled Iot Educational Frameworks: An In-Depth Analysis.' Educational Administration: Theory and Practice 30, no. 4 (2024): 8436-8445.
  8. Gowda, Dankan, D. Palanikkumar, A. S. Malleswari, Sanjog Thapa, and Rama Chaithanya Tanguturi. 'A Comprehensive Study on Drones and Big Data for Supply Chain Optimization Using a Novel Approach.' In 2024 1st International Conference on Advanced Computing and Emerging Technologies (ACET), pp. 1-7. IEEE, 2024.
  9. Sadiq, Ahmed Tariq, Amjed Abbas Ahmed, and Sura Mazin Ali. 'Attacking classical cryptography method using PSO based on variable neighborhood search.' International Journal of Computer Engineering and Technology 5.3 (2014): 34-49.
  10. Alasmary, W., & Ibrahim, A. (2019). Malware Detection in Network Traffic Using Flow-Based Features and Support Vector Machines. International Journal of Computer Applications, 176(6), 25-32.
  11. Rana, S., & Kapoor, R. (2017). The Role of Data Normalization in Malware Detection Using Machine Learning Algorithms. Journal of Computer Science and Technology, 32(5), 926-934.
  12. Gou, J., Zhang, C., & Xie, S. (2020). An Efficient Approach for Handling Missing Data in Network Traffic for Malware Detection. Computer Networks, 170, 107106.
  13. Gowda, V. Dankan, Annepu Arudra, K. M. Mouna, Sanjog Thapa, Vaishali N. Agme, and K. D. V. Prasad. 'Predictive Performance and Clinical Implications of Machine Learning in Early Coronary Heart Disease Detection.' In 2024 2nd World Conference on Communication & Computing (WCONF), pp. 1- 8. IEEE, 2024.
  14. Chen, J., Yang, Y., & Liu, X. (2018). Performance Evaluation of Machine Learning Models for Network Traffic Classification. Journal of Information Security, 9(3), 75-85.
  15. Ghafoor, A., & Ahmed, F. (2019). Malware Detection Using Support Vector Machines: A Comprehensive Review. Computers & Security, 87, 101586.
  16. Hsu, C. W., Chang, C. C., & Lin, C. J. (2003). A Practical Guide to Support Vector Classification. Technical Report, Department of Computer Science, National Taiwan University.
  17. Liu, Y., & Yang, Y. (2021). Grid Search-Based Parameter Optimization for Malware Detection Using SVM. Journal of Cybersecurity and Privacy, 7(2), 78-92.
  18. Liu, X., Wang, Z., & Liu, X. (2019). Combining Ensemble Methods and SVM for Robust Malware Detection in Network Traffic. Journal of Network Security, 17(2), 58-69.
  19. Jakkani, Anil Kumar, Premkumar Reddy, and Jayesh Jhurani. 'Design of a Novel Deep Learning Methodology for IOT Botnet based Attack Detection.' International Journal on Recent and Innovation Trends in Computing and Communication Design 11 (2023): 4922-4927.
  20. Li, J., Yang, Z., & Zhang, X. (2020). Hybrid Models for Malware Detection in Network Traffic. Computational Intelligence and Neuroscience, 2020, 123456.
  21. Xie, Z., & Wei, X. (2021). A Comparative Study of SVM and Deep Learning for Malware Detection in Network Traffic. IEEE Transactions on Network and Service Management, 18(2), 829-840.
  22. Platt, J. C. (1999). Fast Training of Support Vector Machines Using Sequential Minimal Optimization. Advances in Kernel Methods, 185-208.
  23. Gowda, Dankan, et al. 'Quantum Cryptography and Machine Learning: Enhancing Security in AI Systems.' Advancing Cyber Security Through Quantum Cryptography. IGI Global, 2025. 137-174.
  24. Reddy, Premkumar, Yemi Adetuwo, and Anil Kumar Jakkani. 'Implementation of Machine Learning Techniques for Cloud Security in Detection of DDOS Attacks.' International Journal of Computer Engineering and Technology(IJCET) 15.2 (2024).
  25. Agbonyin, Adeola, Premkumar Reddy, and Anil Kumar Jakkani. 'UTILIZING INTERNET OF THINGS (IOT), ARTIFICIAL INTELLIGENCE, AND VEHICLE TELEMATICS FOR SUSTAINABLE GROWTH IN SMALL, AND MEDIUM FIRMS (SMES).' (2024).
  26. Ahmed, Amjed A., et al. 'Deep learning based side channel attack detection for mobile devices security in 5G networks.' Tsinghua Sci. Technol (2024).
  27. Muhammad, Ammar Abdulhassan, et al. 'Adaptive Optimization of Deep Learning Models on AES based Large Side Channel Attack Data.' Alkadhim Journal for Computer Science 2.1 (2024): 72-85.
  28. Ahmed, Amjed A., et al. 'Review on hybrid deep learning models for enhancing encryption techniques against side channel attacks.' IEEE Access (2024).
  29. Mohammed AL-Ghuribi, Sumaia, et al. 'Navigating the Ethical Landscape of Artificial Intelligence: A Comprehensive Review.' International Journal of Computing and Digital Systems 16.1 (2024): 1-11.
Back
Disclaimer: All papers published in IJPS will be indexed on Google Search Engine as per their policy.
Our Head Office
  • Aryavart International University
    Mission Tilla, Dharmanagar, North Tripura, India
  • +91-9555269393
  • info@ijps.in
Quick Links
Powered By Krrypto