Volume 15 , Issue 1 , PP: 385-395, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Sarah H. Rakad 1 * , Abdulkareem Merhej Radhi 2
Doi: https://doi.org/10.54216/JCIM.150130
Email types sorting is one of the most important tasks in current information systems with the purpose to improve the security of messages, allowing for their sorting into different types. This paper aims at studying the Convolution Neural Network and Long Short-Term Memory (CNN-LSTM), Convolution Neural Network and Gated Recurrent Unit (CNN-GRU) and Long Short-Term Memory (LSTM) deep learning models for the classification of emails into categories such as “Normal”, “Fraudulent”, “Harassment” and “Suspicious”. The architecture of each model is discussed and the results of the models’ performance by testing on labelled emails are presented. Evaluation outcomes show substantial gains in precision and throughput to conventional approaches hence inferring to the efficiency of these proposed models for automated email filtration and content evaluation. Last but not the least, the performance of the classification algorithms is evaluated with the help of parameters like Accuracy, precision, recall and F1-Score. From the experiment, the models found out that CNN-LSTM, together with the Term Frequency and Inverse Document Frequency (TF-IDF) feature extraction yielded the highest accuracy. The accuracy, precision, recall and f1-score values are 99. 348%, 99. 5%, 99. 3%, and 99. 2%, respectively.
Email classification , Deep learning , Long short-term memory , Convolution neural network- long short-term memory , Cyber security
[1] Charalambou, E, Bratskas, R, Karkas, G, & Anastasiades A, " Email forensic tools: A roadmap to email header analysis through a cybercrime use case" , Journal of Polish Safety and Reliability Association Summer Safety and Reliability Seminars, Vol. 7, No. 1, 2016.
[2] Tsochataridou, C, Arampatzis, A, & Katos, V, " Improving Digital Forensics Through Data Mining" , In IMMM 2014, The Fourth International Conference on Advances in Information Mining and Management, September, 2016.
[3] Korasidi Andriana Maria, " Authorship Attribution Forensics: Feature selection methods in authorship identification using a small e- mail dataset”, M. Sc. Thesis, University of Athens, 2016.
[4] Bhardwaj, A. K, & Singh, M, “Data mining- based integrated network traffic visualization framework for threat detection”, Neural Computing and Applications, 26(1), 117- 130, 2015.
[5] Alshingiti, Z.; Alaqel, R.; Al-Muhtadi, J.; Haq, Q.E.U.; Saleem, K.; Faheem, M.H. A Deep Learning-Based Phishing Detection System Using CNN, LSTM, and LSTM-CNN. Electronics 2023, 12, 232.
[6] Tsohou, A.; Diamantopoulou, V.; Gritzalis, S.; Lambrinoudakis, C. Cyber insurance: State of the art, trends and future directions. Int. J. Inf. Secur. 2023, 22, 737–748.
[7] Safi, A.; Singh, S. A systematic literature review on phishing website detection techniques. J. King Saud Univ. Comput. Inf. Sci. 2023, 35, 590–611.
[8] Chen, D.; Wawrzynski, P.; Lv, Z. Cyber security in smart cities: A review of deep learning-based applications and case studies. Sustain. Cities Soc. 2021, 66, 102655.
[9] Adebowale, M.A.; Lwin, K.T.; Hossain, M.A. Deep learning with convolutional neural network and long short-term memory for phishing detection. In Proceedings of the 2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), Island of Ulkulhas, Maldives, 26–28 August 2019; pp. 1–8.
[10] Nguyen, M.; Nguyen, T.; Nguyen, T.H. A deep learning model with hierarchical lstms and supervised attention for anti-phishing. CEUR Workshop Proc. 2018, 2124, 29–38.
[11] Coyotes, C.; Mohan, V.S.; Naveen, J.; Vinayakumar, R.; Soman, K.P.; Verma, A.D.R. ARES: Automatic rogue email spotter. In Proceedings of the 1st AntiPhishing Shared Pilot at 4th ACM International Workshop on Security and Privacy Analytics (IWSPA), Tempe, AZ, USA, 1–11 March 2018.
[12] Hiransha, M.; Unnithan, N.A.; Vinayakumar, R.; Soman, K.; Verma, A.D.R. Deep learning based phishing e-mail detection. In Proceedings of the 1st AntiPhishing Shared Pilot at 4th ACM International Workshop Security Privacy Analytics (IWSPA), Tempe, AZ, USA, 1–11 March 2018; pp. 1–5.
[13] Bagui, S.; Nandi, D.; Bagui, S.; White, R.J. Classifying phishing email using machine learning and deep learning. In Proceedings of the 2019 International Conference on Cyber Security and Protection of Digital Services (Cyber Security), Oxford, UK, 3–4 June 2019.
[14] Fang, Y.; Zhang, C.; Huang, C.; Liu, L.; Yang, Y. Phishing Email Detection Using Improved RCNN Model With Multilevel Vectors and Attention Mechanism. IEEE Access 2019, 7, 56329–5634.
[15] Baccouche, A.; Ahmed, S.; Sierra-Sosa, D.; Elmaghraby, A. Malicious text identification: Deep learning from public comments and emails. Information 2020, 11, 312.
[16] Eryılmaz, E.E.; ¸Sahin, D.Ö.; Kılıç, E. Filtering turkish spam using LSTM from deep learning techniques. In Proceedings of the 2020 8th International Symposium on Digital Forensics and Security, ISDFS, IEEE, Beirut, Lebanon, 1–2 June 2020; pp.
[17] Isik, S.; Kurt, Z.; Anagun, Y.; Ozkan, K. Spam E-mail Classification Recurrent Neural Networks for Spam E-mail Classification on an Agglutinative Language. Int. J. Intell. Syst. Appl. Eng. 2020, 8, 221–227.
[18] Alotaibi, R.; Al-Turaiki, I.; Alakeel, F. Mitigating email phishing attacks using convolutional neural networks. In Proceedings of the 2020 3rd International Conference on Computer Applications & Information Security (ICCAIS), IEEE, Riyadh, Saudi Arabia, 19–21 March 2020; pp. 1–6.
[19] Bagui, S.; Nandi, D.; Bagui, S.; White, R.J. Machine learning and deep learning for phishing email classification using one-hot encoding. J. Comput. Sci. 2021, 17, 610–623.
[20] Alhogail, A.; Alsabih, A. Applying machine learning and natural language processing to detect phishing email. Comput. Secur.2021, 110, 10241.
[21] Manaswini, M.; Srinivasu, D.N. Phishing Email Detection Model using Improved Recurrent Convolutional Neural Networks and Multilevel Vectors. Ann. Rom. Soc. Cell Biol. 2021, 25, 16674–16681.
[22] He, D.; Lv, X.; Xu, X.; Yu, S.; Li, D.; Chan, S.; Guizani, M. An effective double-layer detection system against social engineering attacks. IEEE Netw. 2022, 36, 92–98.
[23] Nooraee, M.; Ghaffari, H. Optimization and Improvement of Spam Email Detection Using Deep Learning Approaches. J. Computer. Robot. 2022, 15, 61–70.
[24] Muralidharan, T.; Nissim, N. Improving malicious email detection through novel designated deep-learning architectures utilizing entire email. Neural Networks 2023, 157, 257–27
[25] E. Haddi, X. Liu, and Y. Shi, “The role of text pre-processing in sentiment analysis,” Procedia Comput. Sci., vol. 17, pp. 26–32, 2013.
