Enhancing Trojan Detection with Machine Learning and Deep Learning: Exploratory Data Analysis and Beyond
DOI:
https://doi.org/10.63682/jns.v14i14S.3424Keywords:
Trojan detection, Machine Learning, Deep Learning, Exploratory Data Analysis, Cyber security, Malware detectionAbstract
Trojans are cunning forms of malware that are constantly expanding, posing an increasing threat to the cyber security landscape. As a result, this study embarks on a mission to enhance trojan identification by fusing the strengths of Machine Learning (ML) and Deep Learning (DL) with the crucial methodology of Exploratory Data Analysis (EDA). Our objective is to create a robust trojan detection system that can adjust to the dynamic nature of trojans and act swiftly in the face of new dangers. In this study, we provide a thorough analysis of the trojan detection domain, focusing on malware, current detection methods, and the crucial function that ML and DL play in cybersecurity. We also stress the value of EDA in locating latent data patterns and enhancing feature engineering. In this study, we present a demonstration of our methodical approach, which entails data collection and pre processing, meticulous EDA, ML and DL model creation, and the fusion of these two paradigms. The experimental findings are then explained, focusing the performance indicators and actual case studies that show how beneficial our approach is in the real world. We show the significance of EDA, ML, and DL in defending computer systems against Trojans by explaining the research's findings
Downloads
Metrics
References
Abomhara, M., & Mahmood, A. N. (2014). A review of machine learning methods for malware detection. Journal of Computing and Security, 44, 110-150.
Rosenberg, E. S., & Hutson, J. (2019). Anomaly-based intrusion detection using machine learning. IEEE Transactions on Network and Service Management, 16(4), 1774-1787.
Kumar, D., & Bhatia, S. S. (2018). Malware detection using machine learning techniques: A comprehensive review. Journal of Network and Computer Applications, 95, 1-24.Liang, Y., & Huang, S. (2015). Malware detection with deep neural networks. Proceedings of the ACM on Conference on Computer and Communications Security, 2(1), 11.
Yuan, L., Lu, X., & Wang, D. (2014). Research on malicious code detection technology based on deep learning. International Journal of Security and Its Applications, 8(1), 329-340.
Sobers, A. B., Gruzdz, A., & Sueda, K. (2018). Exploratory data analysis: Applications for malware detection. IEEE Access, 6, 43160-43176.
Alazab, M., Venkatraman, S., & Watters, P. (2018). Deep learning with edge computing for dynamic malware detection in IoT networks. Sensors, 18(10), 3379.
Perdisci, R., Gu, G., & Lee, W. (2008). Using an ensemble of one-class SVM classifiers to harden payload-based anomaly detection systems. Proceedings of the 14th ACM Conference on Computer and Communications Security, 162-175.
Kok, S. P., & Soh, B. (2017). Exploratory data analysis for the detection of network intrusions using K-means clustering. Journal of Information Security and Applications, 36, 31-39.
Mukherjee, A., & Chatterjee, S. (2019). Survey on malware detection techniques: Taxonomy and future directions. Future Generation Computer Systems, 97, 32-53.
(2014). Abomhara, M., and Mahmood, A. N. a survey of malware detection techniques using machine learning. 44, 110–150, Journal of Computing and Security.
Hutson, J., Rosenberg, E. S. (2019). Machine learning-based anomaly detection of intrusions. 1774–1787 in IEEE Transactions on Network and Service Management, 16(4).
In 2018, Kumar, D., and Bhatia, S. S. A thorough examination of malware detection methods utilising machine learning. 95, 1–24, Journal of Network and Computer Applications.
(2015) Liang, Y., Huang, S. Deep neural networks for the detection of malware. Computer and Communications Security Conference Proceedings, 2(1), 11.
Wang, D., Yuan, L., and Lu, X. (2014). research on deep learning-based malware detection systems. 8(1), 329–340, International Journal of Security and Its Applications.
A. B. Sobers, A. Gruzdz, & K. Sueda (2018). Applications for malware detection: exploratory data analysis. 43160–43176. IEEE Access, 6.
(2017). Alazab, M., Venkatraman, S., and Watters. In IoT networks, deep learning and edge computing are used to identify malware dynamically. 18(10), 3379; Sensors.
Gu, G., Lee, W., and Perdisci (2008). Hardening payload-based anomaly detection systems using an ensemble of one-class SVM classifiers. 14th ACM Conference on Computer and Communications Security Proceedings, 162-175.
(2017) Kok, S. P., & Soh, B. K-means clustering is used in exploratory data analysis for the identification of network intrusions. 36, 31–39, Journal of Information Security and Applications.
A. Mukherjee, S. Chatterjee, and others (2019). Taxonomy and future directions for a survey on malware detection methods. 97, 32–53, Future Generation Computer Systems
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
