ML-Based Phishing Website Detection Using Domain Name Features | IJCT Volume 12 – Issue 5 | IJCT-V12I5P78

Phishing attacks remain one of the most pervasive cybersecurity threats, exploiting human vulnerabilities through deceptive websites. Traditional blacklist and heuristic methods fail to detect newly created and zero-day phishing domains, necessitating proactive approaches. This study proposes a machine learning-based detection system leveraging lexical and domain-level features extracted directly from URLs. Two classification algorithms—Decision Tree (DT) and Support Vector Machine (SVM)—were implemented and evaluated using a balanced dataset of 50,000 phishing and legitimate URLs. Results demonstrate that the Decision Tree outperformed SVM across accuracy (97.11% vs. 92.72%), precision (0.9702 vs. 0.9239), and recall (0.9781 vs. 0.9472). The findings highlight the effectiveness of lightweight ML models in real-time phishing prevention, with practical implications for browser integration, enterprise gateways, and security training.

This research demonstrates that machine learning models using lexical and domain-based features effectively detect phishing websites. The Decision Tree classifier achieved a superior balance of accuracy and interpretability compared to SVM. Future research should explore ensemble learning, adversarial robustness, and hybrid approaches combining lexical, host-based, and content features.

1.Mohammad, R.M. et al. (2015). “Phishing Detection Based on URL Features.” Applied Computing and Informatics. 2.Bahnsen, A.C. et al. (2017). “DeepPhish: Detecting Phishing URLs using Deep Learning.” eCrime Researchers Summit. 3.Basit, A. et al. (2021). “Comparative Study of ML Models for Phishing Detection.” IEEE Access. 4.Odonnat, Ambroise (2024). phishing.arff. figshare. Dataset. https://doi.org/10.6084/m9.figshare.26232710.v1 5.Li, X. et al. (2023). “Transformer Models for Phishing Email Detection.” ACM TDSC. 6.Verizon. (2024). Data Breach Investigations Report.

Call for Paper (Hub) Fast Paper Publication IJCT Indexing & Databases Submit Manuscript Call for Paper: Sep–Oct 2025 Call for Paper: Publish Research