Enhancing Cybersecurity through Machine Learning-Based Malicious Website Classification

D.M.Karthik; R.K.Ramachandran; D.R.Rasakumar

doi:https://doi.org/10.47001/CJESR/2026.306005

Authors

D.M.Karthik

Independent Researcher, Salem, Tamilnadu, India

R.K.Ramachandran

Department of Computer Science and Engineering, Government College of Engineering, Salem, Tamilnadu, India

D.R.Rasakumar

Department of Computer Science and Engineering, School of Computing and Informatics VFSTR Deemed to be University, Vadlamudi, India

Abstract

The rapid growth of internet usage and online services has significantly increased the number of malicious websites designed to conduct phishing attacks, distribute malware, steal sensitive information, and compromise user privacy. These cyber threats pose serious challenges to individuals, organizations, and governments by exploiting unsuspecting users through deceptive web pages and fraudulent URLs. Traditional malicious website detection techniques primarily rely on blacklist databases and signature-based approaches. Although these methods effectively identify previously known malicious websites, they are unable to detect newly emerging or zero-day malicious websites, thereby limiting their effectiveness against evolving cyber threats. To overcome these limitations, this paper proposes a Machine Learning-Based Malicious Website Classification framework for enhancing cybersecurity through intelligent URL analysis and predictive classification. The proposed system extracts lexical features from website URLs, including URL length, domain characteristics, special characters, suspicious keywords, subdomain patterns, and structural attributes, to build an effective feature representation without requiring website content analysis. Multiple supervised machine learning algorithms, including Decision Tree, Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression, Naïve Bayes, and ensemble learning techniques, are employed to classify websites as either legitimate or malicious. A comprehensive comparative evaluation is conducted using multiple datasets to assess the classification performance, robustness, and generalization capability of the models across diverse cybersecurity scenarios. Experimental results demonstrate that machine learning models significantly outperform conventional blacklist-based detection methods by accurately identifying both known and previously unseen malicious websites. Among the evaluated classifiers, K-Nearest Neighbors and Random Forest exhibit superior performance in terms of classification accuracy, precision, recall, F1-score, and overall detection reliability across different datasets. The proposed framework provides an intelligent, scalable, and real-time cybersecurity solution capable of improving online threat detection, reducing false-positive rates, and strengthening web security against continuously evolving cyber-attacks. This research contributes to the development of proactive malicious website detection systems that support cybersecurity professionals, internet users, and organizations in mitigating web-based threats through advanced machine learning techniques.

Keywords

Cybersecurity Malicious Website Detection Machine Learning Website Classification URL Analysis Lexical Feature Extraction Phishing Detection Malware Detection Supervised Learning Random Forest K-Nearest Neighbors (KNN) Support Vector Machine (SVM) Logistic Regression Decision Tree.

Citation of this Article

D.M.Karthik, R.K.Ramachandran, & D.R.Rasakumar. (2026). Enhancing Cybersecurity through Machine Learning-Based Malicious Website Classification. Current Journal of Engineering and Science Research. 3(6), 41-50. Article DOI: https://doi.org/10.47001/CJESR/2026.306005

References

M. Bishop, Computer Security: Art and Science, 2nd ed. Boston, MA, USA: Addison-Wesley, 2019.

W. Stallings, Network Security Essentials: Applications and Standards, 7th ed. Pearson, 2022.

C. Seifert and I. Welch, "Phishing Detection Using Machine Learning Techniques," Journal of Information Security, vol. 10, no. 2, pp. 101–115, 2019.

J. Ma, L. Saul, S. Savage, and G. Voelker, "Beyond Blacklists: Learning to Detect Malicious Web Sites from Suspicious URLs," Proc. ACM SIGKDD, 2009, pp. 1245–1254.

N. Sahingoz, E. Buber, O. Demir, and B. Diri, "Machine Learning Based Phishing Detection from URLs," Expert Systems with Applications, vol. 117, pp. 345–357, 2019.

T. Fawcett, "An Introduction to ROC Analysis," Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006.

L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

C. Cortes and V. Vapnik, "Support Vector Networks," Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.

T. Cover and P. Hart, "Nearest Neighbor Pattern Classification," IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21–27, 1967.

P. Domingos and M. Pazzani, "On the Optimality of the Simple Bayesian Classifier," Machine Learning, vol. 29, no. 2–3, pp. 103–130, 1997.

G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning, 2nd ed. Springer, 2021.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.

B. Eshete, A. Villafiorita and K. Weldemariam, "Malicious Website Detection: Effectiveness and Efficiency Issues", 2011 First SysSec Workshop, 2011. Available: 10.1109/syssec.2011.9.

A.Ali Ahmed, "Malicious Website Detection: A Re-view", Journal of Forensic Sciences & Criminal Investigation, vol. 7, no. 3, 2018. Avail-ble:10.19080/jfsci.2018.07.555712.

NortonLifeLock, “Norton,” Norton.com, 2019. https://us.norton.com/internetsecurity-malware-what-are-maliciouswebsites.html.

F. Vanhoenshoven, G. Nápoles, R. Falcon, K. Vanhoof and M. Köppen, "Detecting Malicious URLs using Machine Learning Techniques," 2016 IEEE Symposium Series on Computational Intelligence (SSCI), Athens, Greece, 2016, pp. 1-8, DOI:10.1109/SSCI.2016.7850079.

M. Jordan and T. Mitchell, "Machine learning: Trends, Perspectives, and Prospects", Science, vol. 349, no. 6245, pp. 255-260, 2015. Available:10.1126/science.aaa8415

A.S. Manjeri, K. R., A. M.N.V., and P. C. Nair, "A Machine Learning Approach for Detecting Malicious Websites using URL Features," 2019 3rd International Conference on Electronics, Communication, and Aero-space Technology (ICECA), Coimbatore, India, 2019, pp. 555-561, DOI: 10.1109/ICECA.2019.8821879.

Q. T. Hai and S. O. Hwang, “Detection of Malicious URLs Based on Word Vector Representation and Ngram,” Journal of Intelligent & Fuzzy Systems, vol. 35, no. 6, pp. 5889–5900, Dec. 2018, doi: 10.3233/jifs-169831.

D. SAHOO, C. LIU, and S. HOI, "Malicious URL Detection using Machine Learning: A Survey", Arxiv.org, 2021. [Online]. Available: https://arxiv.org/pdf/1701.07179.pdf.

A.Y. Daeef, R. B. Ahmad, Y. Yacob, and N. Y. Phing, "Wide Scope and Fast Websites Phishing Detection using URLs Lexical Features," 2016 3rd International Conference on Electronic Design (ICED), Phuket, Thailand, 2016, pp. 410-415, doi: 10.1109/ICED.2016.7804679.

Y. Zhauniarovich, I. Khalil, T. Yu, and M. Dacier, "A Survey on Malicious Domains Detection through DNS Data Analysis", ACM Computing Surveys, vol. 51, no. 4, pp. 1-36, 2018. Available: 10.1145/3191329.

K. Rieck, T. Krueger, and A. Dewald, “Cujo: Efficient detection and Prevention of Drive-by-download Attacks,” in Annual Computer Security Applications Conference (ACSAC), 2010, pp. 31–39.

J. Ma, L. K. Saul, S. Savage, and G. M. Voelker, “Beyond Blacklists: Learning to detect Malicious Web-sites from Suspicious URLs.” Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD ’09, 2009, DOI: 10.1145/1557019.1557153.

A.Joshi, L. Lloyd, P. Paul Westin, and S. Seethapathy, "Using Lexical Features for Malicious URL Detection -A Machine Learning Approach", 2019.

H. Kazemian and S. Ahmed, "Comparisons of Ma-chine Learning Techniques for Detecting Malicious Web Pages", Expert Systems with Applications, vol. 42, no. 3, pp. 1166-1177, 2015. Available: 10.1016/j.eswa.2014.08.046.

A.S. Manjeri, K. R., A. M.N.V., and P. C. Nair, "A Machine Learning Approach for Detecting Malicious Websites using URL Features," 2019 3rd International Conference on Electronics, Communication, and Aero-space Technology (ICECA), Coimbatore, India, 2019, pp. 555-561, DOI: 10.1109/ICECA.2019.8821879.