Phishing Website Detection Using Machine Learning

This study focused on the development of an automated phishing website detection system using machine learning techniques. With the increasing reliance on digital platforms and the rapid growth of cyber threats, particularly phishing attacks, there is a critical need for efficient and reliable detection mechanisms. The proposed system addresses this need by leveraging structured website features and applying a data-driven classification approach. The implementation of the Logistic Regression model demonstrated that even a relatively simple algorithm can produce strong and consistent results when supported by well-preprocessed and relevant data. The model achieved an accuracy of 92.45%, along with balanced precision and recall values, indicating its capability to correctly classify both phishing and legitimate websites with minimal error. These results highlight the effectiveness of feature-based analysis, especially attributes related to URL structure, domain characteristics, and security indicators. Another important contribution of this work is the integration of the trained model into a user-friendly interface. This enhances the practical applicability of the system, allowing users to input URLs and receive immediate predictions. Such an approach bridges the gap between theoretical model development and real-world usability, making the system more accessible to non-technical users. The study also reinforces the importance of machine learning in cybersecurity. Compared to traditional detection techniques, the proposed approach offers improved adaptability and the ability to detect previously unseen phishing patterns. While the system is developed in a controlled environment, the results indicate strong potential for deployment in real-world applications. Overall, this research successfully demonstrates that machine learning can serve as an effective tool for phishing detection. It provides a solid foundation for further improvements and highlights the importance of combining data analysis, model development, and system implementation to address modern cybersecurity challenges.

[1] R. M. Mohammad, F. Thabtah, and L. McCluskey, “Phishing websites dataset,” UCI Machine Learning Repository, 2014. [Online]. Available: https://archive.ics.uci.edu/ml/datasets/Phishing+Websites  [2] O. K. 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.  [3] A. Aljofey, Q. Jiang, H. Rasool, and A. Chen, “An effective phishing detection model based on machine learning,” IEEE Access, vol. 8, 2020.  [4] A. K. Jain and B. B. Gupta, “Phishing detection: Analysis of visual similarity based approaches,” Security and Communication Networks, 2016.  [5] S. Marchal, J. François, R. State, and T. Engel, “PhishStorm: Detecting phishing with streaming analytics,” IEEE Transactions on Network and Service Management, vol. 11, no. 4, pp. 458–471, 2014.  [6] J. Ma, L. K. Saul, S. Savage, and G. M. Voelker, “Beyond blacklists: Learning to detect malicious web sites from suspicious URLs,” in Proc. ACM SIGKDD, 2009, pp. 1245–1254.  [7] Symantec Corporation, “Internet Security Threat Report,” 2022. [Online]. Available: https://www.broadcom.com/company/newsroom/press-releases  [8] R. Verma and N. Das, “What’s in a URL: Fast feature extraction and malicious URL detection,” in Proc. IEEE Cybersecurity Conference, 2017.  [9] World Health Organization, “Cybersecurity and digital safety report,” 2021.  [10] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [Online]. Available: https://jmlr.org/papers/v12/pedregosa11a.html  [11] W. McKinney, “Data structures for statistical computing in Python,” in Proc. Python in Science Conference, 2010. [Online]. Available: https://conference.scipy.org/proceedings/scipy2010/mckinney.html  [12] A. Blum, B. Wardman, T. Solorio, and G. Warner, “Lexical feature based phishing URL detection,” in Proc. ACM Workshop, 2010.