Machine Learning-Powered Cyber Threat Detection and Network Intrusion Classification System
Keywords:
Anomaly detection, Cyber security, Cyber threats, Monitoring, Malware Classification, Machine learning security, Network traffic analysis, Real-time threat, Threat intelligenceAbstract
Cyber threats and network intrusions are becoming more advanced, posing serious challenges to both organizations and individuals. Conventional intrusion Identification systems primarily depend on rules that are defined early and signature-based methods, which limit their effectiveness against emerging attack patterns and zero-day vulnerabilities. This paper introduces a ML based approach to cyber threat identification and network intrusion classification, aiming to enhance network security through intelligent data analysis. The system utilizes both supervised learning techniques and unsupervised techniques to categorize network traffic and identify anomalies. Feature selection methods such as Component Analysis Principal and correlation analysis are included to refine input data, improving both detection accuracy and computational performance. Several machine learning models, including Support Vector Machines (SVM), Deep Neural Networks (DNN), and Random Forest, and are trained using datasets such as CICIDS 2017 and NSL-KDD to effectively detect cyber threats. Additionally, an anomaly detection method utilizing auto encoders is implemented to recognize previously unknown attacks. The system's effectiveness is calculated using evaluation metrics such as precision, F1-score, accuracy, and recall, demonstrating its reliability. By offering real-time adaptability and proactive threat mitigation, the proposed model strengthens cyber security defenses, highlighting the potential of machine learning in advancing modern intrusion detection systems beyond traditional methods.
References
R. K. Mahmood, A. I. Mahameed, N. Q. Lateef, H. M. Jasim, A. D. Radhi, S. R. Ahmed, and P. Tupe-Waghmare, "Optimizing network security with machine learning and multi-factor authentication for enhanced intrusion detection," J. Robot. Control (JRC), vol. 5, no. 5, pp. 1502–1524, Aug. 2024. https://journal.umy.ac.id/index.php/jrc/article/view/22508
S. Elsayed, K. Mohamed, and M. A. Madkour, "A comparative study of using deep learning algorithms in network intrusion detection," IEEE Access, Apr. 16, 2024. https://doi.org/10.1109/ACCESS.2024.3389096
R. Basnet, R. Shash, C. Johnson, L. Walgren, and T. Doleck, “Towards Detecting and Classifying Network Intrusion Traffic Using Deep Learning Frameworks.” Apr. 07, 2025. https://isyou.info/jisis/vol9/no4/jisis-2019-vol9-no4-01.pdf
A. Redhu, P. Choudhary, K. Srinivasan, and T. K. Das, "Deep learning-powered malware detection in cyberspace: a contemporary review," Front. Phys., vol. 12, Art. no. 1349463, Mar. 2024. https://doi.org/10.3389/fphy.2024.1349463
M. Khan and L. Ghafoor, "Adversarial machine learning in the context of network security: Challenges and solutions," J. Comput. Intell. Robot., vol. 4, no. 1, pp. 51–63, 2024. https://thesciencebrigade.com/jcir/article/view/118
T. T. Nguyen, Q. V. Nguyen, D. T. Nguyen, D. T. Nguyen, T. Huynh-The, S. Nahavandi, T. T. Nguyen, Q. V. Pham, and C. M. Nguyen, "Deep learning for deepfakes creation and detection: A survey," Comput. Vis. Image Underst., vol. 223, p. 103525, Oct. 1, 2022. https://doi.org/10.1016/j.cviu.2022.103525
A. Sharon, P. Mohanraj, T. E. Abraham, B. Sundan, and A. Thangasamy, "An intelligent intrusion detection system using hybrid deep learning approaches in cloud environment," in Proc. Int. Conf. Comput., Commun., Signal Process., Cham, Switzerland: Springer Int. Publishing, Feb. 24, 2022, pp. 281–298. http://dx.doi.org/10.1007/978-3-031-11633-9_20
D. Gibert, C. Mateu, and J. Planes, "The rise of machine learning for detection and classification of malware: Research developments, trends and challenges," J. Netw. Comput. Appl., vol. 153, p. 102526, Mar. 2020. https://doi.org/10.1016/j.jnca.2019.102526
J. Yu, A. V. Shvetsov, and S. H. Alsamhi, "Leveraging machine learning for cybersecurity resilience in Industry 4.0: Challenges and future directions," IEEE Access, Oct. 17, 2024 https://doi.org/10.1109/ACCESS.2024.3482987
S. Racherla, P. Sripathi, N. Faruqui, M. A. Kabir, M. Whaiduzzaman, and S. A. Shah, "Deep-IDS: A real-time intrusion detector for IoT nodes using deep learning," IEEE Access, May 3, 2024. https://doi.org/10.1109/ACCESS.2024.3396461
J. H. Ring IV, C. M. Van Oort, S. Durst, V. White, J. P. Near, and C. Skalka, "Methods for host-based intrusion detection with deep learning," Digit. Threats: Res. Pract. (DTRAP), vol. 2, no. 4, pp. 1–29, Oct. 15, 2021. https://doi.org/10.1145/3461462
A. Bhattacharyya, S. M. Nambiar, R. Ojha, A. Gyaneshwar, U. Chadha, and K. Srinivasan, "Machine learning and deep learning powered satellite communications: Enabling technologies, applications, open challenges, and future research directions," Int. J. Satellite Commun. Netw., vol. 41, no. 6, pp. 539–588, Nov. 2023. https://doi.org/10.1002/sat.1482
S. Salturk and N. Kahraman, "Deep learning-powered multimodal biometric authentication: Integrating dynamic signatures and facial data for enhanced online security," Neural Comput. Appl., vol. 36, no. 19, pp. 11311–11322, Jul. 2024. https://link.springer.com/article/10.1007/s00521-024-09690-2
G. Kornaros, "Hardware-assisted machine learning in resource-constrained IoT environments for security: Review and future prospective," IEEE Access, vol. 10, pp. 58603–58622, May 30, 2022. https://doi.org/10.1109/ACCESS.2022.3179047
