Optimized Deep Learning Model Using Binary Particle Swarm Optimization for Phishing Attack Detection: A Comparative Study
Article Sidebar
Main Article Content
Abstract
Phishing attacks manipulate users to disclose critical information, resulting in cybersecurity risks. Traditional phishing detection algorithms usually have large false positive rates and poor feature selection, degrading performance. This paper presents an optimized phishing detection framework that integrates binary particle swarm optimization (BPSO)-based feature selection (FS) with deep learning models. Six deep learning architectures were evaluated on the selected feature subset to identify the most effective model for accurate phishing classification. BPSO was used to select suitable attributes on a public Kaggle dataset with 10,000 samples, comprising phishing and legitimate website data with 48 attributes. NumDots, UrlLength, IpAddress, and NoHttps were selected among the 25 features chosen. BPSO was chosen because it effectively reduces feature dimensionality while preserving crucial attributes that enhance classification accuracy. The BPSO optimally selects relevant phishing-related attributes, improving model efficiency and reducing computational complexity. The BPSO technique optimally selects the most relevant features, reducing dataset dimensionality by 48% while maintaining high classification performance. We used six DL models—MLP, 1D-CNN, RNN, LSTM, GRU, and DNN—to test the specified characteristics. The experimental results demonstrate that the DNN model outperforms the other methods through 99.63% accuracy, 99.74% precision, 99.54% recall, and an AUC of 0.9999.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
[1] N. Sun, X. Cheng, C. Li, Y. Liu, J. Wang, and H. He, “Cyber threat intelligence mining for proactive cybersecurity defense: A survey and new perspectives,” IEEE Commun. Surveys Tuts., vol. 25, no. 3, pp. 1748–1774, Jan. 2023, doi: 10.1109/COMST.2023.3273282.
[2] T. Nagunwa, “Comparative analysis of nature-inspired metaheuristic techniques for optimizing phishing website detection,” Analytics, vol. 3, no. 3, pp. 344–367, Aug. 2024, doi: 10.3390/analytics3030019.
[3] P. Pathak and A. K. Shrivas, “Development of proposed model using random forest with optimization technique for classification of phishing website,” SN Comput. Sci., vol. 5, no. 8, Nov. 2024, doi: 10.1007/s42979-024-03388-x.
[4] E. H. Alkhammash, M. Hadjouni, and A. M. Elshewey, “A hybrid ensemble stacking model for gender voice recognition approach,” Electronics, vol. 11, no. 11, p. 1750, 2022, doi: 10.3390/electronics11111750.
[5] A. M. Elshewey, A. A. Alhussan, D. S. Khafaga, E. S. Elkenawy, and Z. Tarek, “EEG‑based optimization of eye state classification using modified‑BER metaheuristic algorithm,” Sci. Rep., vol. 14, no. 1, p. 24489, 2024, doi: 10.1038/s41598-024-74475-5.
[6] S. D. Guptta, X. Liu, A. Alhussan, and M. Elsherif, “Modeling hybrid feature‑based phishing websites detection using machine learning techniques,” Ann. Data Sci., vol. 11, no. 1, pp. 217–242, Mar. 2022, doi: 10.1007/s40745-022-00379-8.
[7] E. Kocyigit et al. , “Enhanced feature selection using genetic algorithm for machine‑learning‑based phishing URL detection,” Appl. Sci., vol. 14, no. 14, p. 6081, Jul. 2024, doi: 10.3390/app14146081.
[8] S. Alnemari and M. Alshammari, “Detecting phishing domains using machine learning,” Appl. Sci., vol. 13, no. 8, p. 4649, Apr. 2023, doi: 10.3390/app13084649.
[9] S. R. A. Samad, M. R. A. Rahman, A. S. Ali, and M. M. A. Hashem, “Analysis of the performance impact of fine‑tuned machine learning model for phishing URL detection,” Electronics, vol. 12, no. 7, p. 1642, Mar. 2023, doi: 10.3390/electronics12071642.
[10] U. A. Butt, M. A. Gondal, A. L. Khan, E. Imran, and R. U. Khan, “Cloud‑based email phishing attack using machine and deep learning algorithm,” Complex Intell. Syst., vol. 9, no. 3, pp. 3043–3070, Jun. 2022, doi: 10.1007/s40747-022-00760-3.
[11] A. Maci, E. Loreto, F. Boninsegna, and M. De Pietro, “Unbalanced web phishing classification through deep reinforcement learning,” Computers, vol. 12, no. 6, p. 118, Jun. 2023, doi: 10.3390/computers12060118.
[12] S. Atawneh and H. Aljehani, “Phishing email detection model using deep learning,” Electronics, vol. 12, no. 20, p. 4261, Oct. 2023, doi: 10.3390/electronics12204261.
[13] Z. Alshingiti, A. A. Elhoseny, H. Alansary, and A. M. El‑Sayed, “A deep learning‑based phishing detection system using CNN, LSTM, and LSTM‑CNN,” Electronics, vol. 12, no. 1, p. 232, Jan. 2023, doi: 10.3390/electronics12010232.
[14] U. Zara, M. Al‑Badarneh, A. Kadri, R. Sultan, and T. Hudaib, “Phishing website detection using deep learning models,” IEEE Access, Jan. 2024, doi: 10.1109/ACCESS.2024.3486462.
[15] D. R. I. M. Setiadi, R. I. Putra, N. A. Nugroho, and E. Mulyadi, “Phishing website detection using bidirectional gated recurrent unit model and feature selection,” J. Future Artif. Intell. Technol., vol. 1, no. 2, pp. 75–83, Jul. 2024, doi: 10.62411/faith.2024-15.
[16] S. Jamal, A. Khan, S. M. Abubakar, and A. N. Mohammed, “An improved transformer‑based model for detecting phishing, spam and ham emails: A large language model approach,” Security Privacy, vol. 7, no. 5, Apr. 2024, doi: 10.1002/spy2.402.
[17] A. Aljofey, M. Elsayed, and A. Shehri, “An effective phishing detection model based on character level convolutional neural network from URL,” Electronics, vol. 9, no. 9, p. 1514, Sep. 2020, doi: 10.3390/electronics9091514.
[18] E. S. Elkenawy, A. A. Alhussan, D. S. Khafaga, Z. Tarek, and A. M. Elshewey, “Greylag goose optimization and multilayer perceptron for enhancing lung cancer classification,” Sci. Rep., vol. 14, no. 1, p. 23784, 2024, doi: 10.1038/s41598-024-72013-x.
[19] A. Mughaid et al. , “An intelligent cyber security phishing detection system using deep learning techniques,” Cluster Comput., vol. 25, no. 6, pp. 3819–3828, May 2022, doi: 10.1007/s10586-022-03604-4.
[20] M. Almousa et al. , “Phishing website detection: How effective are deep learning‑based models and hyperparameter optimization?” Security Privacy, vol. 5, no. 6, Aug. 2022, doi: 10.1002/spy2.256.
[21] L. Lakshmi, R. Kumar, and S. R. Reddy, “Smart phishing detection in web pages using supervised deep learning classification and optimization technique ADAM,” Wireless Pers. Commun., vol. 118, no. 4, pp. 3549–3564, Mar. 2021, doi: 10.1007/s11277-021-08196-7.
[22] F. Aljuaydi, B. K. Behera, A. M. Elshewey, and Z. Tarek, “A deep learning prediction model to predict sustainable development in Saudi Arabia,” Appl. Math., vol. 18, no. 6, pp. 1345–1366, 2024, doi: 10.18576/amis/180615.
[23] D. Han, L. Wang, X. Zhang, and J. Li, “Reflective distributed denial of service detection: A novel model utilizing binary particle swarm optimization—simulated annealing for feature selection and gray wolf optimization‑optimized LightGBM algorithm,” Sensors, vol. 24, no. 19, p. 6179, Sept. 2024, doi: 10.3390/s24196179.
[24] A. J. S. Albahadili, B. Al‑Karaki, S. K. A. Saeed, and M. Al‑Ahmad, “Detection of phishing URLs with deep learning based on GAN‑CNN‑LSTM network and swarm intelligence algorithms,” Signal Image Video Process., vol. 18, nos. 6–7, pp. 4979–4995, Jun. 2024, doi: 10.1007/s11760-024-03204-2.
[25] A. M. Elshewey and A. M. Osman, “Orthopedic disease classification based on breadth‑first search algorithm,” Sci. Rep., vol. 14, no. 1, p. 23368, 2024, doi: 10.1038/s41598-024-73559-6.
[26] T. Karthikeyan et al. , “An effective fraud detection using competitive swarm optimization based deep neural network,” Meas. Sensors, vol. 27, p. 100793, May 2023, doi: 10.1016/j.measen.2023.100793.
[27] P. H. Kyaw et al. , “A systematic review of deep learning techniques for phishing email detection,” Electronics, vol. 13, no. 19, p. 3823, Sep. 2024, doi: 10.3390/electronics13193823.
[28] J. Aljabri et al. , “Hybrid stacked autoencoder with dwarf mongoose optimization for phishing attack detection in internet of things environment,” Alex. Eng. J., vol. 106, pp. 164–171, Jul. 2024, doi: 10.1016/j.aej.2024.06.070.
[29] S. Minocha and B. Singh, “A novel phishing detection system using binary modified equilibrium optimizer for feature selection,” Comput. Electr. Eng., vol. 98, p. 107689, Jan. 2022, doi: 10.1016/j.compeleceng.2022.107689.
[30] G. Mohamed et al. , “An effective and secure mechanism for phishing attacks using a machine learning approach,” Processes, vol. 10, no. 7, p. 1356, Jul. 2022, doi: 10.3390/pr10071356.
[31] F. Feng et al. , “The application of a novel neural network in the detection of phishing websites,” J. Ambient Intell. Humanized Comput., vol. 15, no. 3, pp. 1865–1879, Apr. 2018, doi: 10.1007/s12652-018-0786-3.
[32] K. Bitirgen and Ü. B. Filik, “A hybrid deep learning model for discrimination of physical disturbance and cyber‑attack detection in smart grid,” Int. J. Crit. Infrastruct. Protect., vol. 40, p. 100582, Dec. 2022, doi: 10.1016/j.ijcip.2022.100582.
[33] N. Kunhare et al. , “Particle swarm optimization and feature selection for intrusion detection system,” Sadhana, vol. 45, no. 1, May 2020, doi: 10.1007/s12046-020-1308-5.
[34] S. Jagan et al. , “A meta‑classification model for optimized ZBot malware prediction using learning algorithms,” Mathematics, vol. 11, no. 13, p. 2840, Jun. 2023, doi: 10.3390/math11132840.
[35] A. K. Balyan et al. , “A hybrid intrusion detection model using EGA‑PSO and improved random forest method,” Sensors, vol. 22, no. 16, p. 5986, Aug. 2022, doi: 10.3390/s22165986.
[36] T. R. Alsenani et al. , “Intelligent feature selection model based on particle swarm optimization to detect phishing websites,” Multimed. Tools Appl., vol. 82, no. 29, pp. 44943–44975, Apr. 2023, doi: 10.1007/s11042-023-15399-6.
[37] C. Yang et al. , “IoT botnet attack detection model based on DBO‑Catboost,” Appl. Sci., vol. 13, no. 12, p. 7169, Jun. 2023, doi: 10.3390/app13127169.
[38] S. K. SKTowfek, “CNN‑based multiclass classification for COVID‑19 in chest X‑ray images,” J. Artif. Intell. Metaheuristics, vol. 6, no. 1, pp. 48–55, Jan. 2023, doi: 10.54216/jaim.060105.
[39] M. Abotaleb et al. , “Enhancing stock price prediction accuracy using ARIMA and advanced greylag goose optimizer algorithm,” J. Artif. Intell. Eng. Pract., vol. 1, no. 1, pp. 49–65, Apr. 2024, doi: 10.21608/jaiep.2024.355004.
[40] N. Innab et al. , “Phishing attacks detection using ensemble machine learning algorithms,” Comput. Mater. Continua, vol. 80, no. 1, pp. 1325–1345, Jan. 2024, doi: 10.32604/cmc.2024.051778.
[41] S. A. Elsaid et al. , “Hybrid intrusion detection models based on GWO optimized deep learning,” Concurr. Comput. Pract. Exp., vol. 36, no. 11, 2024, doi: 10.1007/s42452-024-06209-1.
[42] “Anti‑phishing tools: State of the art and detection efficiencies,” Appl. Math. Inf. Sci., vol. 16, no. 6, pp. 929–934, Nov. 2022, doi: 10.18576/amis/160609.
[43] M. A. Elberri et al. , “A cyber defense system against phishing attacks with deep learning game theory and LSTM‑CNN with African vulture optimization algorithm (AVOA),” Int. J. Inf. Secur., vol. 23, no. 4, pp. 2583–2606, May 2024, doi: 10.1007/s10207-024-00851-x.
[44] A. B. Majgave and N. L. Gavankar, “Automatic phishing website detection and prevention model using transformer deep belief network,” Comput. Secur., vol. 147, p. 104071, Aug. 2024, doi: 10.1016/j.cose.2024.104071.
[45] L. Das et al. , “A novel deep learning model‑based optimization algorithm for text message spam detection,” J. Supercomput., vol. 80, no. 12, pp. 17823–17848, May 2024, doi: 10.1007/s11227-024-06148-z.
[46] S. Anupam and A. K. Kar, “Phishing website detection using support vector machines and nature‑inspired optimization algorithms,” Telecommun. Syst., vol. 76, no. 1, pp. 17–32, Nov. 2020, doi: 10.1007/s11235-020-00739-w.
[47] Y. Fouad et al., “IoT traffic parameter classification based on optimized BPSO for enabling green wireless networks,” Eng. Technol. Appl. Sci. Res., vol. 14, no. 6, pp. 18929–18934, Dec. 2024, doi: 10.48084/etasr.9230.
[48] A. M. Elshewey et al., “Water potability classification based on hybrid stacked model and feature selection,” Environ. Sci. Pollut. Res., Mar. 2025, doi: 10.1007/s11356-025-36120-0.
[49] A. M. Elshewey et al., “Prediction of aerodynamic coefficients based on machine learning models,” Model. Earth Syst. Environ., vol. 11, no. 3, Mar. 2025, doi: 10.1007/s40808-025-02355-6.
[50] N. Kamble and N. Mishra, “Hybrid optimization enabled SqueezeNet for phishing attack detection,” Comput. Secur., vol. 144, p. 103901, May 2024, doi: 10.1016/j.cose.2024.103901.
[51] M. Nanda and S. Goel, “URL based phishing attack detection using BiLSTM‑gated highway attention block convolutional neural network,” Multimed. Tools Appl., vol. 83, no. 27, pp. 69345–69375, Jan. 2024, doi: 10.1007/s11042-023-17993-0.
[52] S. Jafari and N. Aghaee‑Maybodi, “Detection of phishing addresses and pages with a data set balancing approach by generative adversarial network (GAN) and convolutional neural network (CNN) optimized with swarm intelligence,” Concurr. Comput. Pract. Exp., vol. 36, no. 11, 2024, doi: 10.1002/cpe.8033.