Phishing is one of the most severe threats to internet security. It utilizes spotted websites to rob users’ passwords and online identities. Generally, phishers use spotted emails or instant messages to attract users to phishing websites. In order to detect phishing attacks in the network, Deep Neural Network (DNN) was introduced. However, the computational complexity of DNN-based phishing attack detection is high because of using irrelevant and redundant features in DNN. So, DNN with Stacked Denoise AutoEncoder (DNN-SDAE) was proposed which reconstructed input features by removing irrelevant and redundant features. Then, the softmax activation function was processed the reconstructed features detect the phishing attack. In this paper, DNN with Ensembling SDAE (DNN-ESDAE) is proposed to reduce the complexity of SDAE and enhance the phishing attack detection accuracy. Initially, Uniform Resource Locator (URL)-based features, Hyper-Text Markup Language (HTML)-based features and domain-based features are extracted by using feature extractor. Then, individual type of features is processed in different SDAE which reconstruct input features. After the ensembling of three SDAE using negative correlation learning, the best selective ensembling is chosen using Shuffled Frog Leaping Optimization Algorithm (SFLOA). Finally, majority voting is employed to combine the results of three SDAE. The experiment is conducted to prove the effectiveness of DNN-ESDAE in terms of accuracy, precision, recall, and f-measure.

Phishing attack detection, Deep Neural Network, Ensembling Stacked Denoise AutoEncoder, Shuffled Frog Leaping Optimization Algorithm, majority voting

[1] K. Parsons, M. Butavicius, P. Delfabbro, M. Lillie, “Predicting susceptibility to social influence in phishing emails”, International Journal of Human-Computer Studies, Vol.128, pp.17-26, 2019.
[2] M. Shukla, S. Sharma, “Analysis of efficient classification algorithm for detection of phishing site”, International Journal of Scientific Research in Computer Sciences and Engineering, Vol.5, Issue.3, pp. 136-141, 2017.
[3] T. Chin, K. Xiong, C. Hu, “Phishlimiter: A Phishing Detection and Mitigation Approach Using Software-Defined Networking”, IEEE Access, Vol.6, pp.42516-42531, 2018.
[4] K. Sumathi, V. Sujatha, “Deep learning based-phishing attack detection”, International Journal of Recent Technology and Engineering (IJRTE), Vol.8, Issue.3, pp.8428-8432, 2019.
[5] H.K. Soni, “Machine learning- A new paradigm of AI”, International Journal of Scientific Research in Network Security and Communication, Vol.7, Issue.3, pp.31-32, 2019.
[6] K. Sumathi, V. Sujatha, “Deep neural network with stacked denoise auto encoder for phishing detection”, International Journal of Machine Learning and Networked Collaborative Engineering (IJMLNCE), Vol.3, Issue.2, pp.114-124, 2019.
[7] I.R.A. Hamid, J. Abawajy, “Hybrid feature selection for phishing email detection”, In the Proceedings of 2011 International Conference on Algorithms and Architectures for Parallel Processing Springer, Berlin, pp.266-275, 2011.
[8] G.A. Montazer, S. ArabYarmohammadi, “Detection of phishing attacks in Iranian e-banking using a fuzzy–rough hybrid system”, Applied Soft Computing, Vol.35, pp.482-492, 2015.
[9] G. Sonowal, K.S. Kuppusamy, “PhiDMA–a phishing detection model with multi-filter approach”, Journal of King Saud University-Computer and Information Sciences, Vol.32, pp.99-112, 2017.
[10] S. Smadi, N. Aslam, L. Zhang, “Detection of online phishing email using dynamic evolving neural network based on reinforcement learning”, Decision Support Systems, Vol.107, pp.88-102, 2018.
[11] P. Yang, G. Zhao, P. Zeng, “Phishing Website Detection Based on Multidimensional Features Driven by Deep Learning”, IEEE Access, Vol.7, pp.15196-15209, 2019.
[12] M. Chatterjee, A.S. Namin, “Detecting Phishing Websites through Deep Reinforcement Learning”, In the proceedings of 2019 IEEE Conference on Annual Computer Software and Applications Conference (COMPSAC), Vol.2, pp.227-232, 2019.
[13] F. Toolan, J. Carthy, “Feature selection for spam and phishing detection”, IEEE eCrime Researchers Summit, pp.1-12, 2010.
[14] S. Garera, N. Provos, M. Chew, A.D. Rubin, “A framework for detection and measurement of phishing attacks”, In the Proceedings of the 2007 ACM workshop on Recurring malcode, pp.1-8, 2007.
[15] M. Lichman, UCI machine learning repository, 2013.