AI-POWERED REAL-TIME PHISHING DETECTION USING HYBRID DEEP LEARNING MODELS

Authors

  • Xushvaqtov Nurzod Tashkent University of Information Technologies Tashkent, Uzbekistan

Keywords:

Phishing Detection, Deep Learning, CNN, LSTM, Real-time Systems, Cybersecurity, Feature Fusion, Edge, Computing

Abstract

This paper presents a novel hybrid deep learning framework for real-time phishing website detection that achieves state-of-the-art performance while maintaining computational efficiency. We propose a unique architecture combining Convolutional Neural Networks (CNN) for spatial feature extraction and Bidirectional Long Short-Term Memory (BiLSTM) networks for temporal pattern recognition. Our model utilizes feature fusion techniques to integrate URL characteristics, HTML content features, and JavaScript behavior patterns. The proposed system achieves 99.3% accuracy on the benchmark Phishing Dataset with a processing time of 8.2 milliseconds per sample, making it suitable for real-time deployment on edge devices. Experimental results demonstrate significant improvements over existing methods, with a 40% reduction in false positives and 35% faster inference times compared to traditional deep learning approaches.

References

Verizon, “2023 data breach investigations report,” Verizon Business, 2023, accessed: 2023-11-15.

R. Rao and S. Kumar, “Deep learning based phishing detection using url and html content,” Expert Systems with Applications, vol. 207, p. 118026, 2022.

W. Jiang, L. Zhang, and H. Chen, “Lstm-based phishing detection with sequential url analysis,” in Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023, pp. 123– 134.

J. Ma, L. K. Saul, S. Savage, and G. M. Voelker, “Learning to detect malicious urls,” ACM Transactions on Intelligent Systems and Technology (TIST), vol. 2, no. 3, pp. 1–24, 2011.

Y. Zhang, J. I. Hong, and L. F. Cranor, “Cantina: a content-based approach to detecting phishing web sites,” in Proceedings of the 16th international conference on World Wide Web, 2007, pp. 639–648.

D. Sahoo, C. Liu, and S. C. Hoi, “Malicious url detection using machine learning: A survey,” arXiv preprint arXiv:1701.07179, 2017.

W. Wang, Y. Li, X. Wang, J. Liu, and X. Zhang, “Deep learning for phishing detection: A comprehensive survey,” IEEE Access, vol. 8, pp. 82771–82784, 2020.

Y. Zhang, S. Wang, and M. Li, “Attention-based deep learning for phishing detection,” Computers & Security, vol. 108, p. 102347, 2021.

M. Carnau, “Phishing dataset,” https://github.com/marcocarnau/ phishing dataset, 2020, accessed: 2023-11-15.

PhishTank, “Phishtank dataset,” https://phishtank.org/developer info. php, 2023, accessed: 2023-11-15.

OpenPhish, “Openphish threat intelligence,” https://openphish.com/, 2023, accessed: 2023-11-15.

J. Kim, S. Park, and H. Lee, “Hybrid deep learning for cyber threat detection,” IEEE Transactions on Dependable and Secure Computing, vol. 19, no. 3, pp. 1872–1885, 2022.

X. Chen, Y. Liu, and W. Zhang, “Real-time phishing detection on edge devices,” in 2023 IEEE International Conference on Edge Computing (EDGE), 2023, pp. 45–52.

R. Patel, A. Singh, and S. Gupta, “Feature fusion techniques for phishing detection,” Journal of Network and Computer Applications, vol. 181, p. 103034, 2021.

Q. Liu, Z. Wang, and T. Zhang, “Attention mechanisms in cybersecurity applications,” Computers & Security, vol. 124, p. 102956, 2023.

R. Singh, P. Kumar, and A. Jain, “Optimization techniques for deep learning on edge devices,” in Proceedings of the 2022 ACM/IEEE Symposium on Edge Computing, 2022, pp. 312–325.

B. B. Gupta, K. Yadav, and I. Razzak, “Benchmark datasets for phishing detection research,” ACM Computing Surveys, vol. 55, no. 9, pp. 1–35, 2023.

S. Tan, W. Li, and J. Zhao, “Adversarial attacks on phishing detection systems,” IEEE Transactions on Information Forensics and Security, vol. 17, pp. 2345–2359, 2022.

Y. Wang, L. Chen, and H. Zhang, “Federated learning for privacypreserving phishing detection,” in 2023 IEEE Symposium on Security and Privacy (SP), 2023, pp. 543–557.

A. Kumar, R. Sharma, and P. Singh, “Multi-modal phishing detection using deep learning,” Neural Computing and Applications, vol. 33, pp.

–12360, 2021.

M. Ali, S. Khan, and A. Rahman, “Efficient neural architecture for realtime security applications,” Journal of Systems Architecture, vol. 130, p. 102678, 2022.

Published

2026-01-30 — Updated on 2026-01-30

Versions

Issue

Section

Articles