Optimization Of Social Media Phishing Detection Models

Wenni Syafitri (Scopus ID: 57200085316), Guntoro Guntoro, Ahmad Zamsuri, Idel Waldelmi

Abstract


Phishing is one of the most dangerous attacks in the cyber world. Very few researchers have focused on social media phishing, although SMS phishing can be related to the messaging features available on various social media platforms. This study will utilize PSO and PCA techniques to optimize the performance of RF in social media phishing. This study will compare the performance of PSO and RF with that of PCA and RF. An optimized phishing message detection model was built using NLP, incorporating TF-IDF for feature extraction, PCA and PSO for feature optimization, and Random Forest as a classifier to distinguish phishing messages from normal messages. The RF model optimized by PSO produces nearly balanced metrics: precision (0.9877), recall (0.9728), and F1 (0.9802), all of which are high. The RF model with PCA optimization achieves a slightly lower Accuracy (0.9639) and the lowest Precision (0.9585). Although there were no significant differences in the classification process, PSO and PCA made a real contribution to future research development.

Keywords


PCA;Phishing;PSO;Random Forest;SMS;Social Media

References


A. Odeh, Q. A. Al-Haija, A. Aref, and A. A. Taleb, “Comparative Study of CatBoost, XGBoost, and LightGBM for Enhanced URL Phishing Detection: A Performance Assessment,” JISIS, vol. 13, no. 4, pp. 1–11, Dec. 2023, doi: 10.58346/JISIS.2023.I4.001.

S. S. Patil, N. M. Shekokar, and S. C. Iyer, “Design of Intelligent Feature Selection Technique for Phishing Detection,” IIUMEJ, vol. 26, no. 1, pp. 254–277, Jan. 2025, doi: 10.31436/iiumej.v26i1.3337.

S. Alsufyani and S. Alajmani, “A Deep Learning for Arabic SMS Phishing Based on URLs Detection,” ijacsa, vol. 16, no. 1, 2025, doi: 10.14569/IJACSA.2025.0160138.

P. Preeti and P. Sharma, “Enhancing phishing URL detection through comprehensive feature selection: a comparative analysis across diverse datasets,” IJEECS, vol. 36, no. 2, p. 1182, Nov. 2024, doi: 10.11591/ijeecs.v36.i2.pp1182-1188.

S. M. Alshahrani, “URL Phishing Detection Using Particle Swarm Optimization and Data Mining,” CMC, vol. 73, no. 3, pp. 5625–5640, 2022, doi: 10.32604/cmc.2022.030982.

H. Shaiba, J. S. Alzahrani, M. M. Eltahir, R. Marzouk, H. Mohsen, and M. Ahmed Hamza, “Hunger Search Optimization with Hybrid Deep Learning Enabled Phishing Detection and Classification Model,” Computers, Materials & Continua, vol. 73, no. 3, pp. 6425–6441, 2022, doi: 10.32604/cmc.2022.031625.

E. Zhu, Z. Chen, J. Cui, and H. Zhong, “MOE/RF: A Novel Phishing Detection Model Based on Revised Multiobjective Evolution Optimization Algorithm and Random Forest,” IEEE Trans. Netw. Serv. Manage., vol. 19, no. 4, pp. 4461–4478, Dec. 2022, doi: 10.1109/TNSM.2022.3162885.

R. C and T. M, “Improved Random Forest Algorithm using Chicken Swarm Optimization for Phishing Website Classification Model,” SSRG-IJEEE, vol. 10, no. 4, pp. 141–151, Apr. 2023, doi: 10.14445/23488379/IJEEE-V10I4P114.

K. Subashini and D. V. Narmatha, “MANTA RAY FORAGING OPTIMIZATION ALGORITHM WITH DEEP LEARNING ASSISTED AUTOMATED PHISHING URL DETECTION MODEL,” Journal of Theoretical and Applied Information Technology, vol. 101, no. 24, 2023.

B. B. Gupta et al., “A Hybrid CNN-Brown-Bear Optimization Framework for Enhanced Detection of URL Phishing Attacks,” CMC, vol. 81, no. 3, pp. 4853–4874, 2024, doi: 10.32604/cmc.2024.057138.

P. Hemannth, M. Chinta, S. S. Satya, and P. Sri Aneelaja Devasena, “A Phishing URL Detection Model based on Horse Herd Optimization and Random Forest Algorithms,” in 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN), Salem, India: IEEE, May 2024, pp. 926–931. doi: 10.1109/ICPCSN62568.2024.00156.

M. Diviya, M. Subramanian, and D. Gopala Krishnan, “An optimized phishing detection model using hybrid feature selection and a fine-tuned narrow neural network with dynamic jaya optimization to overcome cyberthreats,” Eng. Res. Express, vol. 7, no. 1, p. 015202, Mar. 2025, doi: 10.1088/2631-8695/ada1a4.

R. Abdillah, Z. Shukur, M. Mohd, T. S. M. Z. Murah, I. Oh, and K. Yim, “Performance Evaluation of Phishing Classification Techniques on Various Data Sources and Schemes,” IEEE Access, vol. 11, pp. 38721–38738, 2023, doi: 10.1109/ACCESS.2022.3225971.

B. N. Almousa and D. M. Uliyan, “Anti-Spoofing in Medical Employee’s Email using Machine Learning Uclassify Algorithm,” IJACSA, vol. 14, no. 7, 2023, doi: 10.14569/IJACSA.2023.0140727.

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.

R. Meléndez, M. Ptaszynski, and F. Masui, “Comparative Investigation of Traditional Machine-Learning Models and Transformer Models for Phishing Email Detection,” Electronics, vol. 13, no. 24, p. 4877, Dec. 2024, doi: 10.3390/electronics13244877.

C. Thapa et al., “Evaluation of Federated Learning in Phishing Email Detection,” Sensors, vol. 23, no. 9, p. 4346, Apr. 2023, doi: 10.3390/s23094346.

Q. Qi, Z. Wang, Y. Xu, Y. Fang, and C. Wang, “Enhancing Phishing Email Detection through Ensemble Learning and Undersampling,” Applied Sciences, vol. 13, no. 15, p. 8756, Jul. 2023, doi: 10.3390/app13158756.

P. Yasinta Roesmiatun and A. Zahra, “Enhancing detection of zero-day phishing email attacks in the Indonesian language using deep learning algorithms,” Bulletin EEI, vol. 14, no. 1, pp. 505–512, Feb. 2025, doi: 10.11591/eei.v14i1.8759.

R. Brindha, S. Nandagopal, H. Azath, V. Sathana, G. Prasad Joshi, and S. Won Kim, “Intelligent Deep Learning Based Cybersecurity Phishing Email Detection and Classification,” Computers, Materials & Continua, vol. 74, no. 3, pp. 5901–5914, 2023, doi: 10.32604/cmc.2023.030784.




DOI: http://dx.doi.org/10.24014/coreit.v11i1.37602

Refbacks

  • There are currently no refbacks.


Bookmark and Share


Creative Commons License  site stats  
Jurnal CoreIT by http://ejournal.uin-suska.ac.id/index.php/coreit/ is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.