Cyber Attack Detection Using a Supervised ML Techniques
Main Article Content
Abstract
Introduction: The rapid growth of digital technologies and interconnected systems has significantly increased the risk of cyberattacks across networks and information infrastructures. Traditional signature-based intrusion detection systems often fail to identify sophisticated and zero-day attacks. Supervised machine learning techniques provide an effective solution by learning patterns from labeled historical data to distinguish between normal and malicious activities. These models can analyze large volumes of network traffic and system logs with improved accuracy and adaptability. Therefore, supervised machine learning has emerged as a powerful approach for enhancing cyberattack detection and strengthening cybersecurity defenses.
Objectives: The primary objective of this study is to develop an effective cyberattack detection system using supervised machine learning techniques. It aims to train and evaluate various classification algorithms to accurately distinguish between normal and malicious network activities. The study seeks to compare the performance of different supervised models using metrics such as accuracy, precision, recall, and F1-score. Another objective is to identify the most efficient model with minimal false positives and false negatives.
Methods: The hybrid ensemble–based cyber attack detection methodology integrates data preprocessing, feature optimization, multiple classifiers, and ensemble learning to deliver a high-performance and adaptive cyber security solution capable of identifying both known and emerging threats effectively.
Results: The experimental results demonstrate that supervised machine learning models effectively detect cyberattacks with high accuracy and reliability. Among the evaluated algorithms, ensemble methods achieved superior performance compared to individual classifiers. The models showed strong detection rates with reduced false positives and improved overall classification metrics. These findings confirm that supervised learning techniques significantly enhance cyberattack detection capability in modern cybersecurity systems.
Conclusions: The study concludes that supervised machine learning techniques provide an efficient and reliable approach for cyberattack detection. The evaluated models demonstrated strong classification performance, particularly ensemble methods, in identifying malicious activities. Proper feature selection and data preprocessing further enhance detection accuracy and reduce false alarms. Overall, supervised learning-based systems offer a scalable and robust solution for strengthening modern cybersecurity defenses.
Article Details
References
S. Kaushik, A. Bhardwaj, A. Almogren, S. Bharany, A. Altameem, A. Ur Rehman, S. Hussen, and H. Hamam, “Robust machine learning based intrusion detection system using simple statistical techniques in feature selection,” Scientific Reports, vol. 15, art. 3970, Feb. 2025.
S. K. R. Mallidi and R. R. Ramisetty, “Advancements in training and deployment strategies for AI-based intrusion detection systems in IoT: a systematic literature review,” Discover Internet Things, vol. 5, art. 8, Jan. 2025.
A. H. Salem, S. M. Azzam, O. E. Emam, and A. Abohany, “Advancing cybersecurity: a comprehensive review of AI-driven detection techniques,” J. Big Data, vol. 11, art. 105, Aug. 2024.
M. Bendegúz Bankó et al., “Advancements in machine learning-based intrusion detection in IoT: research trends and challenges,” Algorithms, vol. 18, no. 4, art. 209, Apr. 2025.
P. Czaja, B. Gdowski, M. Niemiec, et al., “Cybersecurity challenges and opportunities of machine learning-based artificial intelligence,” Neural Comput. Appl., vol. 37, pp. 27931–27956, Nov. 2025.
R. Almuhanna and S. Dardouri, “A deep learning/machine learning approach for anomaly based network intrusion detection,” Front. Artif. Intell., vol. 8, 1625891, Sept. 2025.
Y. K. Saheed, A. A. Usman, F. D. Sukat, and M. A. Abdulrahman, “Hybrid machine learning–based intrusion detection for zero-day attack prevention in digital education networks,” Int. J. Secur. Educ., 2025.
I. Koukoulis, I. Syrigos, and T. Korakis, “Self-Supervised transformer-based contrastive learning for intrusion detection systems,” arXiv preprint, May 2025.
S. Jamshidia, A. Nikanjama, K. W. Nafia, F. Khomha, and R. Rasta, “Application of deep reinforcement learning for intrusion detection in Internet of Things: a systematic review,” arXiv preprint, Apr. 2025.
R. Akinie, N. K. B. Gyimah, M. Bhavsar, and J. Kelly, “Fine-tuning federated learning-based intrusion detection systems for transportation IoT,” arXiv preprint, Feb. 2025.
S. Elouardi, M. Jouhari, and A. Motii, “OptiFLIDS: optimized federated learning for energy-efficient intrusion detection in IoT,” arXiv preprint, Oct. 2025.
I. J. Vourganas and A. L. Michala, “Applications of machine learning in cyber security: a review,” J. Cybersecur. Priv., vol. 4, no. 4, pp. 972–992, Nov. 2024.
S. Ogunbadejo, O. A. Ayilara-Adewale, and O. Alade, “Machine learning methods for intrusion detection: a comprehensive survey,” Int. J. Sci. Res. Manag., vol. 13, no. 07, pp. 2446–2456, Jul. 2025.
“Machine learning-based intrusion and anomaly detection for enhancing security in IoT networks using BoT-IoT dataset,” Int. J. Eng. Comput. Sci., vol. 6, no. 1, pp. 241–248, 2024.
A. Hozouri, A. Mirzaei, and M. Effatparvar, “A comprehensive survey on intrusion detection systems with advances in machine learning,” Discover Artif. Intell., vol. 5, art. 314, Nov. 2025.
(Conference) X. Meng, “Advanced AI and ML techniques in cybersecurity: supervised and unsupervised learning, and neural networks in threat detection,” in Proc. 2nd Int. Conf. Mach. Learn. Autom., Applied and Comput. Eng., vol. 82, 2024.
J. Shen, W. Yang, Z. Chu, J. Fan, D. Niyato, and K.-Y. Lam, “Effective intrusion detection in heterogeneous Internet-of-Things networks via ensemble knowledge distillation-based federated learning,” arXiv preprint, Jan. 2024.
(Springer) A. Alansary, S. Ayyad, F. Talaat, et al., “Emerging AI threats in cybercrime: a review of zero-day attacks via machine, deep, and federated learning,” Knowl. Inf. Syst., vol. 67, pp. 10951–10987, Nov. 2025.
(Elsevier) N. Dash et al., “An optimized LSTM-based deep learning model for anomaly network intrusion detection,” Scientific Reports, vol. 15, no. 1, art. 1554, 2025.
A. Gueriani, H. Kheddar, and A. C. Mazari, “Adaptive cyber-attack detection in IIoT using attention-based LSTM-CNN models,” in Proc. Int. Conf. Telecommun. Intell. Syst. (ICTIS), 2024.