An Effective Detection Approach for Phishing URL Using ResMLP
Keywords:
URL, Feature Engineering, Residual MLP (ResMLP), Random Forest, Naïve Bayes, Next.jsAbstract
The proliferation of phishing and malware-laden URLs poses an ever-increasing threat to Internet users, enterprises, and critical infrastructure. Traditional URL filtering techniques often rely on static blacklists or shallow machine-learning models, which struggle to generalize to novel attack patterns. In this work, we present a full-stack Malicious URL Detection system combining a Next.js front-end with a Python-based back-end that extracts thirty-two lexical, domain-registration, HTML/JavaScript, and reputation features from user-submitted URLs. Paper details the end-to-end architecture, feature engineering strategies, ResMLP training regimen, and comprehensive evaluation, establishing a template for next-generation URL security platforms.
Downloads
References
Aslam, N., Ahmed, S., Khan, A., & Riaz, H. (2024). AntiPhishStack: LSTM-based Stacked Generalization Model for Optimized Phishing URL Detection. IEEE Transactions on Information Forensics and Security, 19, 1125–1138.
Liu, W., Zhang, Y., & Chen, X. (2023). PyraTrans: Attention-Enriched Pyramid Transformer for Malicious URL Detection. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2348–2360.
Li, J., Zhou, P., & Wang, L. (2023). Fed-urlBERT: Client-side Lightweight Federated Transformers for URL Threat Analysis. IEEE Transactions on Dependable and Secure Computing. Advance online publication.
Liu, Q., Sun, Y., & Li, T. (2023). Malicious URL Detection via Pretrained Language Model Guided Multi-Level Feature Attention Network. Knowledge-Based Systems, 272, 109492.
Kausar, F., Ahmad, R., & Khan, M. (2021). DL-URLDetector: A Deep Learning Framework for Malicious URL Detection. IEEE Access, 9, 78012–78023.
Al-Dujaili, A. H., & Hu, X. (2018). Adversarial Deep Learning for Robust Detection of Malicious URLs. Proceedings of the 2018 IEEE International Conference on Data Mining Workshops (ICDMW), 1124–1131.
Chen, H., Xu, B., & Wu, J. (2018). URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection. Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM), 491–500.
Ma, J., Saul, L. K., Savage, S., & Voelker, G. M. (2009). 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, 1245–1254.
Alazab, M., Vinayakumar, R., & Soman, K. P. (2019). Deep Recurrent Neural Network-Based Botnet Detection in Executable and Script Files. IEEE Transactions on Network and Service Management, 16(2), 608–621.
Sharif, M., Ristenpart, T., & Chmiel, M. (2016). PhishZoo: Detecting Phishing URLs using Visual Similarity. Proceedings of the 25th USENIX Security Symposium, 1019–1034.
Ganesh, C., Thomas, A., & Vinod, P. (2020). PhishAri: Automatic Realtime Phishing URL Detection. IEEE International Conference on Cyber Security and Protection of Digital Services (Cyber Security), 1–8.
Bozorgi, M., et al. (2010). Beyond Heuristics: Learning to Classify Websites as Malicious or Benign. Proceedings of the 2010 SIAM International Conference on Data Mining, 90–101.
Le, B., Sharma, V., & Balachandran, A. (2011). Scalable Feature Extraction for URL Classification. Proceedings of the 20th International Conference on World Wide Web, 1014–1022.
Bergholz, A., De Beer, J., Glahn, S., Moens, M.‐F., Paaß, G., & Strobel, S. (2008). Improved Phishing Detection using Model‐based URL Classification. Proceedings of the 5th Conference on Email and Anti‐Spam (CEAS).
Thomas, K., Grier, C., Song, D., & Paxson, V. (2011). Suspended Accounts in Retrospect: An Analysis of Twitter Spam. Proceedings of the 2011 ACM SIGCOMM Conference on Internet Measurement Conference, 243–258.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
