Penerapan VGG16 pada identifikasi Website Phishing berbasis analisis visual
Keywords:
Phishing, VGG16, deep learning, SMOTE, computer vision, keamanan siberAbstract
Serangan phishing merupakan salah satu ancaman keamanan siber yang paling signifikan, dengan kerugian global mencapai miliaran dollar setiap tahunnya. Metode deteksi tradisional berbasis URL sering kali gagal mengidentifikasi website phishing yang menggunakan domain legitimate atau teknik obfuscation. Penelitian ini mengusulkan pendekatan deteksi phishing berbasis analisis visual menggunakan arsitektur VGG16 dengan teknik SMOTE (Synthetic Minority Over-sampling Technique) untuk mengatasi ketidakseimbangan kelas. Model VGG16 yang telah dilatih pada ImageNet digunakan sebagai feature extractor, menghasilkan representasi fitur 256 dimensi dari screenshot website. Untuk mengatasi masalah imbalanced dataset, SMOTE diterapkan pada fitur yang telah diekstrak sebelum proses klasifikasi. Dataset terdiri dari screenshot website legitimate dan phishing yang dikumpulkan dari berbagai sumber publik. Hasil eksperimen menunjukkan bahwa model yang diusulkan mencapai akurasi 94.23%, precision 93.67%, recall 94.89%, F1-score 94.27%, dan AUC-ROC 96.84%. Implementasi Grad-CAM (Gradient-weighted Class Activation Mapping) memberikan visualisasi eksplanasi tentang area website yang menjadi fokus model dalam pengambilan keputusan. Sistem ini diintegrasikan dalam aplikasi web berbasis Gradio untuk memudahkan penggunaan secara real-time. Hasil penelitian menunjukkan bahwa pendekatan visual menggunakan deep learning dapat menjadi solusi efektif untuk deteksi phishing, terutama dalam mengidentifikasi website yang meniru tampilan visual brand terkenal.
Downloads
References
Abuhamad, M., Abusnaina, A., Nyang, D., & Mohaisen, D. (2019). Sensor-based continuous authentication of smartphones’ users using behavioral biometrics: A contemporary survey. IEEE Internet of Things Journal, 8(1), 65-84.
Adebowale, M. A., Lwin, K. T., & Hossain, M. A. (2023). Intelligent phishing detection scheme using deep learning algorithms. Journal of Enterprise Information Management, 36(3), 747-766.
Aljofey, A., Jiang, Q., Qu, Q., Huang, M., & Niyigena, J. P. (2020). An effective phishing detection model based on character level convolutional neural network from URL. Electronics, 9(9), 1514.
Chiew, K. L., Yong, K. S. C., & Tan, C. L. (2018). A survey of phishing attacks: Their types, vectors and technical approaches. Expert Systems with Applications, 106, 1-20.
Chowdhury, N. H., Adam, M. T. P., & Teubner, T. (2020). Time pressure in human cybersecurity behavior: Theoretical framework and countermeasures. Computers & Security, 97, 101931.
Feng, F., Zhou, Q., Shen, Z., Yang, X., Han, L., & Wang, J. (2019). The application of a novel neural network in the detection of phishing websites. Journal of Ambient Intelligence and Humanized Computing, 1-15.
Gandotra, E., Gupta, D., & Sahu, S. (2021). Improved detection of phishing websites using machine learning. Procedia Computer Science, 189, 460-469.
Gibert, D., Mateu, C., & Planes, J. (2020). The rise of machine learning for detection and classification of malware: Research developments, trends and challenges. Journal of Network and Computer Applications, 153, 102526.
Jain, A. K., & Gupta, B. B. (2018). A novel approach to protect against phishing attacks at client side using auto-updated white-list. EURASIP Journal on Information Security, 2018(1), 1-11.
Khonji, M., Iraqi, Y., & Jones, A. (2013). Phishing detection: A literature survey. IEEE Communications Surveys & Tutorials, 15(4), 2091-2121.
Sahingoz, O. K., Buber, E., Demir, O., & Diri, B. (2019). Machine learning based phishing detection from URLs. Expert Systems with Applications, 117, 345-357.
Smadi, S., Aslam, N., & Zhang, L. (2018). Detection of online phishing email using dynamic evolving neural network based on reinforcement learning. Decision Support Systems, 107, 88-102.
Varshney, G., Misra, M., & Atrey, P. K. (2016). A survey and classification of web phishing detection schemes. Security and Communication Networks, 9(18), 6266-6284.
Yang, P., Zhao, G., & Zeng, P. (2019). Phishing website detection based on multidimensional features driven by deep learning. IEEE Access, 7, 15196-15209.
Bahnsen, A. C., Bohorquez, E. C., Villegas, S., Vargas, J., & González, F. A. (2017). Classifying phishing URLs using recurrent neural networks. In 2017 APWG Symposium on Electronic Crime Research (eCrime) (pp. 1-8). IEEE.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618-626).
Wu, C. Y., Kuo, C. C., & Yang, C. S. (2019). A phishing detection system based on machine learning. In 2019 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW) (pp. 1-2). IEEE.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Anti-Phishing Working Group (APWG). (2023). Phishing Activity Trends Report, 4th Quarter 2023. [cited 2026 Feb 5]. Available from: https://apwg.org/trendsreports/
