Analysis and Classification of Cyberattack Patterns Using a Decision Tree Algorithm: A Synthetic-Data-Based Study

• Radwan M Marwan

  Department of Information Technology ,Higher Institute of Science and Technology, Tajoura, Libya

  Author

Cyber-attacks present a serious threat to the security of web applications and online services. Artificial Intelligence (AI) offers effective approaches for analyzing attack patterns and classifying different types of cyber-attack. This paper explores the effectiveness of the Decision Tree algorithm in classification tasks involving phishing, SQL injection (SQLi), denial-of-service and distributed denial-of-service (DoS/DDoS), and password-related attack techniques. The experiments were performed in the Python programming language using artificially generated data sets. Accuracy, confusion matrices, class-wise F1-scores, and feature importance were evaluated to assess the model’s performance, identify significant features, and analyze classification errors. The results showed accuracy rates of 85.0%, 95.5%, 99.0%, and 52.0% in phishing, SQLi, DoS/DDoS, and password-related attack classification tasks, respectively. These results highlight the model’s inconsistency in the recognition task of the four selected attack categories and emphasize the complexity of distinguishing between password-related attack classes. The paper provides a comprehensive comparison of how the Decision Tree algorithm can utilize the input features to classify attack patterns in controlled experimental conditions. However, the use of artificially generated data sets with specific attack patterns may impact the accuracy and applicability of the results. The findings of this study contribute to the growing body of research on the application of AI algorithms in cybersecurity domains to detect and classify cyber-attacks. However, further research is needed to validate these results on larger-scale studies and real-world data sets. Comparing the performance of different algorithms can help identify the strengths and weaknesses of each approach to enhance the accuracy and efficiency of cyber-attack detection and classification. Additionally, the results of this research emphasize the importance of having high-quality data and a well-defined problem statement when developing effective solutions for detecting and classifying cyber-attacks.

1. Radwan M Marwan, Department of Information Technology ,Higher Institute of Science and Technology, Tajoura, Libya

   Department of Information Technology ,Higher Institute of Science and Technology, Tajoura, Libya

Ahmadi, S. (2024). AI in the detection and prevention of distributed denial of service (DDoS) attacks. International Journal of Advanced Computer Science and Applications, 15(10). https://doi.org/10.14569/IJACSA.2024.0151004 DOI: https://doi.org/10.14569/IJACSA.2024.0151004

Al-Odat, Z. (2025). Optimized distributed gradient boosting with explainable artificial intelligence for real-time ransomware detection in networked environments. International Journal of Electrical and Electronic Engineering & Telecommunications, 14(4). DOI: https://doi.org/10.18178/ijeetc.14.4.233-242

Blockeel, H., Devos, L., Frénay, B., Nanfack, G., & Nijssen, S. (2023). Decision trees: From efficient prediction to responsible AI. Frontiers in Artificial Intelligence, 6, Article 1124553. https://doi.org/10.3389/frai.2023.1124553 DOI: https://doi.org/10.3389/frai.2023.1124553

Chakraborty, A., Biswas, A., & Khan, A. K. (2023). Artificial intelligence for cybersecurity: Threats, attacks and mitigation. In Artificial intelligence for societal issues (pp. 3–25). Springer. https://doi.org/10.1007/978-3-031-12419-8_1 DOI: https://doi.org/10.1007/978-3-031-12419-8_1

Ferdous, J., Islam, R., Mahboubi, A., & Islam, M. Z. (2024). AI-based ransomware detection: A comprehensive review. IEEE Access, 12, 136666–136695. https://doi.org/10.1109/ACCESS.2024.3461965 DOI: https://doi.org/10.1109/ACCESS.2024.3461965

Foley, J. (2026). Cybersecurity future threats in artificial intelligence: A comprehensive analysis. Journal of Advanced Artificial Intelligence, Engineering and Technology, 2(1). https://doi.org/10.56147/aaiet.2.1.113 DOI: https://doi.org/10.56147/aaiet.2.1.113

George, R., & Zeratsion, E. (2025). Detection of SSH brute-force attacks using machine learning: A comparative study with Fail2Ban and PAM Tally2 [Master’s thesis, University West].

Hamza, A. A., & Al-Janabi, R. J. S. (2024). Detecting brute force attacks using machine learning. BIO Web of Conferences, 97, Article 00045. https://doi.org/10.1051/bioconf/20249700045 DOI: https://doi.org/10.1051/bioconf/20249700045

Ismaeel, M., Lokhande, P., & Kotiyal, B. (2025). Enhancing web security detection with AI-driven mitigation techniques. In Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS-2025) (pp. 181–194). Atlantis Press. https://doi.org/10.2991/978-94-6463-852-3_12 DOI: https://doi.org/10.2991/978-94-6463-852-3_12

Kalgude, K. (2022). Bug detection using artificial intelligence and cyber security [Master’s dissertation, Solent University].

Kang, G. (2025). Artificial intelligence for threat detection: Leveraging deep learning to identify zero-day attacks in real time. Universal Library of Engineering Technology, 2(4), 74–79. https://doi.org/10.70315/uloap.ulete.2025.0204013 DOI: https://doi.org/10.70315/uloap.ulete.2025.0204013

Kaushal, H. (2024). XSS exploit generation using AI. International Journal of Research Publication and Reviews, 5(3), 4875–4881.

Kumari, P., Raj, R., Bhandari, H., Goenka, K., & Anjana, R. (2026). AI based cyber threats and vulnerability detection, prevention and prediction system. International Journal for Research in Applied Science & Engineering Technology, 14(6), 85–95. https://doi.org/10.22214/ijraset.2026.83342 DOI: https://doi.org/10.22214/ijraset.2026.83342

Mereani, F. A., & Howe, J. M. (2018). Detecting cross-site scripting attacks using machine learning. In Advanced machine learning technologies and applications (Vol. 723, pp. 200–210). Springer. https://doi.org/10.1007/978-3-319-74690-6_20 DOI: https://doi.org/10.1007/978-3-319-74690-6_20

Njie, B., & Gabriouet, L. (2024). Machine learning for cross-site scripting (XSS) detection: A comparative analysis of machine learning models for enhanced XSS detection [Bachelor’s thesis, Dalarna University]. DiVA. https://www.diva-portal.org/smash/get/diva2%3A1883365/FULLTEXT01.pdf

Patil, P. J., Kulkarni, S., & Kulkarni, V. T. (2026). AI-generated phishing attacks and detection methods. International Journal of Scientific Research in Engineering and Management, 10(6).

Pamarthi, K. (2020). Artificial intelligence and machine learning techniques to control SQL injection attacks. Journal of Scientific and Engineering Research, 7(4), 259–267.

Radaković, M. U., & Marjanović, M. D. (2023). Analyzing a Python programming example of building an artificial intelligence machine learning model for detecting cyber-attacks—Benefits and challenges. Tehnika, 78(2), 187–194. https://doi.org/10.5937/tehnika2302187R DOI: https://doi.org/10.5937/tehnika2302187R

Sinchana, H. C., & Thejaswini, M. N. (2025). AI based phishing attack detection. International Research Journal of Modernization in Engineering Technology and Science, 7(10), 218–221.

Sreedharan, R., & Sampath, A. K. (2026, July 28). Prediction of SQL injection using machine learning [Preprint]. Research Square. https://doi.org/10.21203/rs.3.rs-10122490/v1 DOI: https://doi.org/10.21203/rs.3.rs-10122490/v1

Zunaid, M., Puneeth, M. P., Abhishek, P., Kumar, R. P., & Rahaman, M. T. R. (2026). Phishing website detection using URL-based machine learning for real-time browser security. International Journal of Advanced Research in Computer and Communication Engineering, 15(4). https://doi.org/10.17148/IJARCCE.2026.154274

• PDF

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.