Comparison of Kernel Functions in Support Vector Machine (SVM) Method for Phishing Website Detection

Muhammad Farhan Said, Norma Muhtar, Bahriddin Abapihi, Arman Arman, Muhammad Kabil Djafar, Herdi Budiman

Abstract


Phishing is a rapidly growing form of cybercrime that poses a significant threat to internet users. Therefore, an effective and accurate detection method is essential. This study aims to analyze and compare the performance of several kernel functions within the Support Vector Machine (SVM) method for detecting phishing websites. The kernel functions used include linear, polynomial, Radial Basis Function (RBF), and sigmoid. The dataset is evaluated using stratified 5-fold cross-validation, with F1-score as the primary performance metric. The results show that the RBF kernel achieves the highest performance, with the best F1-score of 94.64%, followed by the polynomial kernel. The linear kernel performs reasonably well on nearly linearly separable data, while the sigmoid kernel shows the lowest and least stable performance. Based on these findings, the RBF kernel is recommended as the most suitable choice for phishing website detection using the SVM method.

 


Keywords


F1-score; Kernel function; Phishing; Support vector machine.

Full Text:

PDF

References


M. Arif, B. Dewanto, M. Fathurrahman, D. R. Firdaus, and A. Setiawan, “Penipuan Penambah Followers Instagram : Analisis Serangan Phising dan Dampaknya pada Keamanan Data,” J. Internet Softw. Eng., vol. 1, no. 4, pp. 1–11, 2024.

F. Yudha, A. Muhammad, and P. Muryadi, “Perancangan Aplikasi Pengujian Celah Keamanan Pada Aplikasi Berbasis Web,” CyberSecurity dan Forensik Digit., vol. 1, no. 1, pp. 1–6, 2018.

A. Farhansyah, “Mengatasi Ancaman Phishing di Era Digital: Tantangan dan Upaya di Indonesia,” KBR. Accessed: Jan. 19, 2025. [Online]. Available: https://kbr.id/ragam/mengatasi-ancaman-phishing-di-era-digital-tantangan-dan-upaya-di-indonesia

T. G. Laksana, S. Mulyani, I. Komputer, J. Informatika, and U. Bhayangkara, “Pengetahuan Dasar Identifikasi Dini Deteksi Serangan Kejahatan Siber Untuk Mencegah Pembobolan Data Perusahaan,” J. Jukim, vol. 3, no. 1, pp. 109–122, 2024.

D. Aksu and A. Abdulwakil, “Detecting Phishing Websites Using Support Vector Machine Algorithm,” PressAcademia, vol. 5, no. 1, pp. 139–142, 2017, doi: 10.17261/Pressacademia.2017.582.

D. Tao, D. Jinran, X. Aidong, X. Chuanmao, L. Boyu, and H. Chao, “Phishing Detection System Based on the SVM Active Learning Algorithm,” in 2023 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON), Bangalore: IEEE, 2023, pp. 1–3.

L. Hamel, Knowledge Discovery with Support Vector Machines. New Jersey: John Wiley & Sons, Inc, 2009. doi: 10.1002/9780470503065.

Y. Jian and Q. Zhao, Machine Learning Techniques. Beijing: Publishing House of Electronics Industry, 2009.

Z. Lin and L. Yan, “A support vector machine classifier based on a new kernel function model for hyperspectral data,” GIScience Remote Sens., vol. 53, no. 1, pp. 85–101, 2016, doi: 10.1080/15481603.2015.1114199.

N. R. Feta and A. R. Ginanjar, “Komparasi Fungsi Kernel Metode Support Vector Machine Untuk Pemodelan Klasifikasi Terhadap Penyakit Tanaman Kedelai,” BRITech, vol. 1, no. 1, pp. 33–39, 2019.

D. Wahyudi, M. Niswar, and A. A. P. Alimuddin, “Website Phising Detection Application Using Support Vector Machine (SVM),” vol. 5, no. 2, 2022.

V. I. Santoso, G. Virginia, Y. Lukito, U. Kristen, and D. Wacana, “Penerapan Sentiment Analysis Pada Hasil Evaluasi Dosen Dengan Metode Support Vector Machine,” J. Transform., vol. 14, no. 2, pp. 79–83, 2017.

S. Raschka and V. Mirjalili, Python Machine Learning, 2nd ed. Birmingham: Packt Publishing Ltd, 2015.

T. Wahyono and Y. Heryadi, Machine Learning (Konsep dan Implementasinya). Yogyakarta: Penerbit Gava Media, 2020.

H. J. Dikkers, “Support vector machines in ordinal classification: An application to corporate credit scoring,” Neural Netw. World, vol. 15, no. 6, pp. 491–507, 2005.

V. N. Vapnik, The Nature of Statistical Learning Theory, 2nd ed. New York: Springer, 2000. doi: 10.1007/978-1-4757-3264-1.

B. Ghojogh, A. L. I. Ghodsi, U. Ca, and M. Crowley, “Reproducing Kernel Hilbert Space, Mercer’s Theorem, Eigenfunctions, Nystrom Method, and Use of Kernels in Machine Learning: Tutorial and Survey,” 2010, doi: 10.48550.

Y. Widyaningsih, G. P. Arum, and K. Prawira, “Application of K-fold Cross Validation in Determining the Best Negative Binomial Regression Model,” BAREKENG J. Ilmu Mat. dan Terap., vol. 15, no. 2, pp. 315–322, 2021, doi: 10.30598.

J. Allen, H. Liu, S. Iqbal, and D. Zheng, “Deep learning-based photoplethysmography classification for peripheral arterial disease detection : a proof-of-concept study,” Physiol. Meas., vol. 42, no. 5, pp. 1–9, 2021.

F. Hilmiyah, “Prediksi Kinerja Mahasiswa Menggunakan Support Vector Machine Untuk Pengelola Program Studi Di Perguruan Tinggi ( Studi Kasus : Program Studi Magister Statistika ITS ),” INSTITUT TEKNOLOGI SEPULUH NOPEMBER, 2017.

I. Markoulidakis, I. Rallis, I. Georgoulas, G. Kopsiaftis, A. Doulamis, and N. Doulamis, “Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem,” Technologies, vol. 9, no. 4, pp. 81–103, 2021.

M. Imani and H. R. Arabnia, “Hyperparameter Optimization and Combined Data Sampling Techniques in Machine Learning for Customer Churn Prediction : A Comparative Analysis,” Technologies, vol. 11, no. 6, pp. 1–26, 2023.

N. Safitri, D. Kusnandar, and S. Martha, “Implementasi Algoritma K-Nearest Neighbor Dengan Normalisasi Z-Score Dalam Klasifikasi Penerima Bantuan Sosial Desa Serunai,” Bul. Ilm. Math. Stat. dan Ter., vol. 13, no. 1, pp. 99–106, 2024.

A. Hannousse and S. Yahiouche, “Web page phishing detection,” Mendeley Data. Accessed: Nov. 12, 2024. [Online]. Available: https://data.mendeley.com/datasets/c2gw7fy2j4/3

S. S. Shafin, “An Explainable Feature Selection Framework for Web Phishing Detection with Machine Learning,” Data Sci. Manag., 2024, doi: 10.1016/j.dsm.2024.08.004.




DOI: https://doi.org/10.15548/jostech.v6i1.13680

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 JOSTECH Journal of Science and Technology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.