The week's pick
Random Articles
Reseach Article
HPDnet: A Hybrid Deep Learning Architecture Combining Bidirectional LSTMs and Heuristic Features for Phishing Email Classification
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 139 |
| Year of Publication: 2026 |
| Authors: Parul Patel |
10.5120/ijca87b9dca7919c
|
Parul Patel . HPDnet: A Hybrid Deep Learning Architecture Combining Bidirectional LSTMs and Heuristic Features for Phishing Email Classification. International Journal of Computer Applications. 187, 139 ( Aug 2026), 22-25. DOI=10.5120/ijca87b9dca7919c
Abstract
Phishing emails are one of the most common cybersecurity threats and continue to cause significant financial losses. Traditional rule-based email filters are becoming less effective because attackers constantly change the content and structure of phishing emails. This paper presents HPDnet, a hybrid deep learning model for phishing email detection that combines BiLSTM-based text analysis with handcrafted features such as URL count, urgency words, generic greetings, and formatting patterns. The model merges these features to improve phishing detection accuracy while maintaining interpretability. The paper also describes the data preprocessing, model architecture, training process, and performance evaluation using a labeled phishing email dataset. The proposed approach demonstrates that combining deep learning with domain-specific features provides an effective and practical solution for phishing email classification.
References
- I. Fette, N. Sadeh, and A. Tomasic, “Learning to detect phishing emails,” in Proc. 16th Int. Conf. World Wide Web (WWW '07), Banff, AB, Canada, 2007, pp. 649–656.
- Akinyelu, A. A., & Adewumi, A. O. (2014). Classification of phishing email using random forest machine learning technique. Journal of Applied Mathematics, 2014.
- Halgas, L., Agrafiotis, I., & Nurse, J. R. C. (2019). Catching the Phish: Detecting Phishing Attacks using Recurrent Neural Networks (RNNs). In International Conference on Detection of Intrusions and Malware, and Vulnerability Assessment (pp. 317-336). Springer.
- Bagui, S., & Nandi, N. (2021). Machine learning and deep learning for phishing email classification using one-hot encoding. Journal of Computer Science, 17.
- Salloum, Said & Gaber, Tarek & Vadera, Sunil & Shaalan, Khaled. (2022). A Systematic Literature Review on Phishing Email Detection Using Natural Language Processing Techniques. IEEE Access. 10. 65703-65727. 10.1109/ACCESS.2022.3183083.
- Chen, P., & Kuo, L. (2021). Federated Phish Bowl: LSTM-based decentralized phishing email detection. arXiv.
- Tooher, P., & Lallie, H. (2025). A two-stage deep learning framework for AI-driven phishing email detection based on persuasion principles. Computers, 14(12), 523.
- Rashed, S., & Ozcan, C. (2026). A Novel Dual-Layer Deep Learning Architecture for Phishing and Spam Email Detection. Electronics, 15(3), 630. https://doi.org/10.3390/electronics15030630
- Hemannth, P. & Chinta, Mukesh & Satya, S. & Devasena, P. (2024). A Phishing Email Detection Model Based on Horse Herd Optimization and Random Forest Algorithms. 1-6. 10.1109/APCIT62007.2024.10673699.
- Palo Alto Networks. Phishing email classifier in Cortex XSOAR. https://www.paloaltonetworks.com/blog/security-operations/phishing-email-classifier-in-cortex-xsoar/
Index Terms
Keywords