Phishing URLs Classification Using Deep Learning Approach

Hajara Musa, Abdulsalam Ya'u Gital, Abdulkadir Hamidu Alkali, Abubakar Umar, Muhammad Zaharadeen Ahmed

Abstract


In recent times, numerous approaches have been proposed for classifying and detecting phishing URLs. While these methods have recorded great successes, most of them are based on content based approaches which has poor generalization ability against new unseen URLS or classical machine learning techniques requiring domain knowledge experts and substantial future engineering. To overcome these limitations, recently, Deep Learning (DL) approaches which offer the ability to automatically capture the semantic or sequential patterns in URLs have been proposed by several studies. This paper reviews and compares the state-of-the-art DL approaches for phishing URLs classification focusing on Recurrent Neural Networks (RNN) and its variants. It has been observed from the experimental results on 60,000 URLs dataset that Gated Recurrent Unit (GRU) model outperforms the basic RNN, and its other variants (LSTM, BiLSTM and, BiGRU) in terms of accuracy, precision, recall, AUC, training, and testing time. Hence the GRU model can be regarded as the first choice for the phishing URL classification in the future work.


Full Text:

PDF

References


H. Le, Q. Pham, D. Sahoo, and S. C.H. Hoi, “URLNet: Learning a URL representation with deep learning for malicious URL detection,” Proceedings of the ACM Symposium on Principles of Distributed Computing, Washington, DC, July 25-27, 2017, 1-13.

PhishTank: An anti-phishing site. Online. Available: https://www.phishtank.com, (Accessed on 5 August, 2022).

A. A. Aminu, A. Abdulkarim, A.Yahaya, and A. M. Turaki, "Detection of phishing websites using Random Forest and XGBoost algorithms," International Journal of Pure and Applied Sciences, vol. 2, no. 3 (2019): 1-14.

Z. Erzhou, Z. Chen, J. Cui, and H. Zhong, "MOE/RF: A Novel Phishing Detection Model based on Revised Multi-Objective Evolution Optimization Algorithm and Random Forest." IEEE Transactions on Network and Service Management, (2022).

G. Al-Mekhlafi, Z., B. A. Mohammed, M. Al-Sarem, F. Saeed, T. Al-Hadhrami, M. T. Alshammari, A. Alreshidi, and T. S. Alshammari. "Phishing websites detection by using optimized stacking ensemble model." Computer Systems Science and Engineering 41, no. 1 (2022): 109-125.

S. Anupam, and A. K. Kar, “Phishing website detection using support vector machines and nature-inspired optimization algorithms,” Telecommunication Systems,76(1), 2021, pp.17-32.

G. Ekta, and D. Gupta, "An efficient approach for phishing detection using machine learning," In Multimedia Security, pp. 239-253. Springer, Singapore, 2021.

A. Ali, Q. Jiang, Q. Qu, M. Huang, and J. Niyigena, "An effective phishing detection model based on character level convolutional neural network from URL," Electronics 9, no. 9 (2020): 1514.

X. Pingfan, "A Transformer-based Model to Detect Phishing URLs." arXiv preprint arXiv:2109.02138 (2021).

Z. Erzhou, Q. Yuan, Z. Chen, X. Li, and X. Fang, "CCBLA: a Lightweight Phishing Detection Model Based on CNN, BiLSTM, and Attention Mechanism," Cognitive Computation (2022): 1-14.

A. Saad, A. Alotaibi, and O. Alsaleh, "PDGAN: Phishing Detection with Generative Adversarial Networks." IEEE Access 10 (2022): 42459-42468.

L. Yann, Y. Bengio, and G. Hinton. "Deep learning." nature 521, no. 7553 (2015): 436-444.

J. L. Elman, “Finding structure in time,” Cognitive Science, 14(2), (1990), 179–211. doi:10.1207/ s15516709cog1402_1

B. Su and S. Lu, “Accurate recognition of words in scenes without character segmentation using recurrent neural network,” Pattern Recogn 2017; 63: 397–405

RNN and its Variants in Handling Sequence Data & Time-Series Data [online], Available:URL, (Accessed on )

Gers FA, Schmidhuber J, Cummins F. Learning to forget: Continual prediction with LSTM. Neural Comput 2000; 12(10):2451–71.

S. Hochreiter, and J. Schmidhuber,”Long short-term memory,” Neural Computation, 9(8), (1997), 1735–1780. doi:10.1162/neco.1997.9.8.1735 PMID:9377276

Y. Imrana, Y. Xiang, L. Ali, Z. Abdul-Rauf, Hu, Y.-C. Kadry, S. S. Lim, “χ 2 -BidLSTM: A Feature Driven Intrusion Detection System Based on χ 2 Statistical Model and Bidirectional LSTM,” Sensors 2022, 22, 2018. https://doi.org/10.3390/ s22052018.

W. Youdao, S. Addepalli, and Y. Zhao, "Recurrent neural networks and its variants in remaining useful life prediction," IFAC-PapersOnLine 53, no. 3 (2020): 137-142.

C. Kyunghyun, B V. Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, "Learning phrase representations using RNN encoder-decoder for statistical machine translation," arXiv preprint arXiv:1406.1078 (2014)

B. Yun, J. Xie, C. Liu, Y.Tao, B. Zeng, and C. Li, "Regression modeling for enterprise electricity consumption: A comparison of recurrent neural network and its variants," International Journal of Electrical Power & Energy Systems 126 (2021): 106612.

M. Schuster, K Paliwal, “Bidirectional recurrent neural networks,“ IEEE Trans. Signal Process. 1997, 45, 2673–2681. [CrossRef]

A. Graves, A. Mohamed, and G. E. Hinton, “Speech recognition with deep recurrent neural networks,” In Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 26–31 May 2013; pp. 6645–6649.

L. Xinyu, Y. Wang, X. Wang, H. Xu, C. Li, and X. Xin, "Bi-directional gated recurrent unit neural network based nonlinear equalizer for coherent optical communication system," Optics Express 29, no. 4 (2021): 5923-5933.

L. Pengpeng, A. Luo, J. Liu, Y. Wang, J. Zhu, Y. Deng, and J. Zhang, "Bidirectional gated recurrent unit neural network for Chinese address element segmentation," ISPRS International Journal of Geo-Information 9, no. 11 (2020): 635.

R. Tomas, and L. Dovydaitis, "Detection of phishing URLs by using deep learning approach and multiple features combinations," Baltic journal of modern computing 8, no. 3 (2020): 471-483.

B. A. Correa, E. C. Bohorquez, S. Villegas, J. Vargas, and F. A. González, "Classifying phishing URLs using recurrent neural networks," In 2017 APWG symposium on electronic crime research (eCrime), pp. 1-8. IEEE, 2017.

http://www.alexa.com/topsites

http://www.dmoz.org/

http://www.phishtank.com/

K. Rieck, T. Krueger and A. Dewald, “Cujo: Efficient detection and prevention of drive-by-download attacks,” In Proceedings of the 26th Annual Computer Security Applications Conference. ACM, (2010), pp. 31–39.


Refbacks

  • There are currently no refbacks.