Citation :

Alaa Kamel Ali, Mohsen Rezvani, "Optimized and Explainable Multimodal Deep Learning Framework for Accurate Phishing Website Detection," International Journal of Electronics and Communication Engineering, vol. 13, no. 5, pp. 97-108, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I5P110

Abstract

Phishing websites remain a significant threat to online users by exploiting deceptive visual layouts, manipulated HTML content, and misleading structural designs to obtain sensitive information. Existing detection approaches mainly rely on single-modal features and often function as black-box systems, which limits their effectiveness against advanced phishing strategies and reduces user trust. This paper proposes an optimized and explainable multimodal deep learning framework for accurate phishing website detection. The proposed model integrates Bidirectional Long Short-Term Memory (BiLSTM) networks for sequential HTML analysis, Graph Convolutional Networks (GCN) for capturing DOM structural dependencies, and Convolutional Neural Networks (CNN) for extracting visual features from webpage screenshots. To enhance training stability and overall performance, Ant Colony Optimization (ACO) is employed to automatically tune critical hyperparameters. In addition, Shapley Additive exPlanations (SHAP) are incorporated to interpret model decisions by quantifying the contribution of each feature modality. Extensive experiments conducted on a large-scale phishing dataset demonstrate that the proposed framework outperforms conventional single-modal and hybrid models, achieving improved accuracy and F1-score. The results confirm that the integration of multimodal learning, metaheuristic optimization, and explainable AI provides a reliable and transparent solution for phishing website detection.

Keywords

Explainable Artificial Intelligence, Multimodal Learning, Phishing Detection, Deep Learning, Hyperparameter Optimization.

References

1. Muhammad Usman Javeed et al., “Phishing Website URL Detection Using A Hybrid Machine Learning Approach,” Journal of Computing & Biomedical Informatics, vol. 9, no. 1, pp. 1-9, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Bryan Lim et al., “EXPLICATE: Enhancing Phishing Detection through Explainable AI and LLM-Powered Interpretability,” arXiv Preprint, pp. 1-9, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Eleni Kytidou et al., “Machine Learning Techniques for Phishing Detection: A Review of Methods, Challenges, and Future Directions,” Intelligent Decision Technologies, vol. 19, no. 6, pp. 4356-4379, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Saif Wali Ali Alsudani et al., “Enhancing Spam Detection: A Crow-Optimized FFNN with LSTM for Email Security,” Wasit Journal of Computer and Mathematics Science, vol. 3, no. 1, pp. 28-39, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Alexey Vulfin et al., “A Multimodal Phishing Website Detection System using Explainable Artificial Intelligence Technologies,” Machine Learning and Knowledge Extraction, vol. 8, no. 1, pp. 1-43, 2026.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Alexey Vulfin et al., “Do We Really Need Reference-Based Phishing Detection? Unleashing the Power of GNN,” 2025 9^th Network Traffic Measurement and Analysis Conference (TMA), Copenhagen, Denmark, pp. 1-4, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Husnain Mansoor Butt et al., “Detecting Phishing URLs Using Hybrid Deep Learning Models,” International Journal for Electronic Crime Investigation, vol. 9, no. 1, pp. 1-14, 2025.
   [CrossRef] [Publisher Link]
8. Brahim Khalil Sedraoui et al., “Cybersecurity in E-Learning: A Literature Review on Phishing Detection Using ML and DL Techniques,” 2025 International Conference on Networking and Advanced Systems (ICNAS), El Tarf, Algeria, pp. 1-10, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Zeinab Shahbazi, Rezvan Jalali, and Maryam Molaeevand, “AI-Based Phishing Detection and Student Cybersecurity Awareness in the Digital Age,” Big Data and Cognitive Computing, vol. 9, no. 8, pp. 1-20, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Alsadig Hadi Alsadig, and Md Oqail Ahmad, “Phishing URL Detection Using Deep Learning with CNN Models,” 2024 Second International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI), Coimbatore, India, pp. 768-775, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. J. Govindaraaj, “The Role of Explainable AI in Understanding Phishing Susceptibility,” Journal of Recent Trends in Computer Science and Engineering, vol. 12, no. 1, pp. 1-6, 2024.
    [Google Scholar] [Publisher Link]
12. Qazi Emad ul Haq, Muhammad Hamza Faheem, and Iftikhar Ahmad, “Detecting Phishing URLs Based on a Deep Learning Approach to Prevent Cyber-Attacks,” Applied Sciences, vol. 14, no. 22, pp. 1-17, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Haifeng Jiang et al., “D-PhishNet: A Dual-Branch Network for URL and HTML Feature Fusion in Phishing Webpage Detection,” Computer Networks, vol. 271, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Yun Lin et al., “Phishpedia: A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages,” 30^th USENIX Security Symposium (USENIX Security 21), pp. 3793-3810, 2021.
15. [Google Scholar] [Publisher Link]
16. Ruofan Liu et al., “Inferring Phishing Intention via Webpage Appearance and Dynamics: A Deep Vision Based Approach,” 31^st USENIX Security Symposium (USENIX Security 22), pp. 1-18, 2022.
    [Google Scholar] [Publisher Link]
17. Tristan Bilot, Grégoire Geis, and Badis Hammi, “PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks,” Proceedings of the 19^th International Conference on Security and Cryptography Secrypt, Lisbon, Portugal, vol. 1, pp. 428-435, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Khandaker Mohammad Mohi Uddin et al., “Explainable Machine Learning for Phishing Site Detection: A High-Efficiency Approach using Boosting Models and Shap,” The Journal of Engineering, vol. 2025, no. 1, pp. 1-18, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Scott M. Lundberg, and Su-In Lee, “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems, vol. 30, 2017.
    [Google Scholar] [Publisher Link]
20. Sakib Shahriar Shafin, “An Explainable Feature Selection Framework for Web Phishing Detection with Machine Learning,” Data Science and Management, vol. 8, no. 2, pp. 127-136, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Maria Carla Calzarossa, Paolo Giudici, and Rasha Zieni, “An Assessment Framework for Explainable AI with Applications to Cybersecurity,” Artificial Intelligence Review, vol. 58, pp. 1-19, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Shaimaa Ahmed Elsaid et al., “Hybrid Intrusion Detection Models based on GWO Optimized Deep Learning,” Discover Applied Sciences, vol. 6, pp. 1-34, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Santosh Kumar Birthriya, Priyanka Ahlawat, and Ankit Kumar Jain, “Intelligent Phishing Website Detection: A CNN–SVM Approach with Nature-Inspired Hyperparameter Tuning,” Cyber Security and Applications, vol. 3, pp. 1-12, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Faiz Akram et al., Integrating Artificial Bee Colony Algorithms for Deep Learning Model Optimization: A Comprehensive Review, Solving with Bees, pp. 73-102, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Fujiao Ji et al., “Evaluating the Effectiveness and Robustness of Visual Similarity-Based Phishing Detection Models,” 34^th USENIX Security Symposium (USENIX Security 25), 2025.
    [Google Scholar] [Publisher Link]
26. Padmalochan Panda, Alekha Kumar Mishra, and Deepak Puthal, “A Novel Logo Identification Technique for Logo-Based Phishing Detection,” Future Internet, vol. 14, no. 8, pp. 1-17, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Saad Al-Ahmadi, “A Deep Learning Technique for Web Phishing Detection Combined URL Features and Visual Similarity,” International Journal of Computer Networks & Communications, pp. 1-14, 2020.
    [Google Scholar] [Publisher Link]
28. Saif Wali Ali Alsudani, and Ghassan Khudair Saud, “Recurrent Neural Network Optimized by Grasshopper for Accurate Audio Data-Based Diagnosis of Parkinson’s Disease,” Wasit Journal for Pure Sciences, vol. 4, no. 2, pp. 56-75, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Jun-Ho Yoon, Seok-Jun Buu, and Hae-Jung Kim, “Phishing Webpage Detection via Multi-Modal Integration of HTML DOM Graph Modeling and URL Feature Analysis,” Electronics, vol. 13, no. 16, pp. 1-21, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]