Implementasi Intrusion Prevention System Berbasis Variational Autoencoder untuk Mencegah Judi Online pada Jaringan Komunitas
DOI:
https://doi.org/10.55123/storage.v5i3.8826Keywords:
Variational Autoencoder, Deep Neural Network, Intrusion Prevention System, Judi Online, Keamanan Jaringan, Encrypted Traffic Classification, Deteksi Anomali, API MikrotikAbstract
Fenomena perjudian online menimbulkan dampak negatif yang masif di Indonesia, baik secara finansial maupun psikologis. Penelitian ini bertujuan untuk mengembangkan IPS (Intrusion Prevention System) berbasis pembelajaran mesin guna melakukan aksi pencegahan secara preventif terhadap pengguna jaringan yang mengakses situs judi online, termasuk yang menggunakan teknik penyembunyian terenkripsi. Penelitian ini menggunakan metode kuantitatif eksperimental dengan memanipulasi variabel fitur pada dataset serta mengoptimalkan arsitektur VAE (Variational Autoencoder) dan DNN (Deep Neural Network). Hasil penelitian menunjukkan bahwa model VAE mampu melakukan rekonstruksi data dan mengelompokkan trafik judi online dengan trafik normal secara presisi, yang dibuktikan melalui visualisasi plot t-SNE. Pada tahap klasifikasi, model DNN mencapai akurasi keseluruhan sebesar 80,80%. Evaluasi spesifik per skenario menunjukkan rata-rata akurasi sebesar 95,13% untuk label judi online (presisi 0,69, recall 0,91, F1-score 0,78) dan 87,69% untuk label normal (presisi 0,93, recall 0,75, F1-score 0,83). Sistem pemantauan trafik yang dikembangkan juga telah terintegrasi dengan router MikroTik melalui API, sehingga fungsi pemblokiran otomatis pada level jaringan dapat beroperasi dengan baik.
Downloads
References
Mayradevi, I.A.P. and Tobing, D.H. 2024. Faktor-faktor yang Memengaruhi Perilaku Judi Online pada Remaja: Narrative Literature Review. Jurnal Psikologi Perseptual 9(1), pp. 4–26. doi: 10.24176/perseptual.v9i1.11940.
Gu, Z., Gou, G., Liu, C., Yang, C., Zhang, X., Li, Z. and Xiong, G. 2024. Let gambling hide nowhere: Detecting illegal mobile gambling apps via heterogeneous graph-based encrypted traffic analysis. Computer Networks 243, p. 110278. doi: 10.1016/j.comnet.2024.110278.
Antonio, J.C., Ong, A.K.S., Diaz, J.F.T., Cahigas, M.M.L. and Gumasing, Ma.J.J. 2025. The perceived risk and return, curiosity, and control analysis of online gambling intention among Gen Z and Millennials using extended UTAUT3. Entertainment Computing 52(1), p. 100918. doi: 10.1016/j.entcom.2024.100918
Monroy, S.S., Gupta, A.K. and Wahlstedt, G. 2023. Detection of Malicious DNS-over-HTTPS Traffic: An Anomaly Detection Approach using Autoencoders. doi: 10.48550/arXiv.2310.11325.
Alkasassbeh Mouhammd and Almseidin, M. 2023. Machine Learning Techniques for Accurately Detecting the DNS Tunneling. In: Arai, K. ed. Intelligent Computing. Cham: Springer Nature Switzerland 711(1), pp. 352–364. doi: 10.1007/978-3-031-37717-4_24.
Alzighaibi, A.R. 2023. Detection of DoH Traffic Tunnels Using Deep Learning for Encrypted Traffic Classification. Computers 12(3), pp. 47–57. doi: 10.3390/computers12030047.
Guerra-Manzanares, A., Caprolu, M. and Di Pietro, R. 2025. A comprehensive review on machine learning-based VPN detection: Scenarios, methods, and open challenges. Computer Science Review 58, p. 100781. doi: 10.1016/j.cosrev.2025.100781.
Azam, Z., Islam, Md.M. and Huda, M.N. 2023. Comparative Analysis of Intrusion Detection Systems and Machine Learning-Based Model Analysis Through Decision Tree. IEEE Access 11(10185955), pp. 80348–80391. doi: 10.1109/ACCESS.2023.3296444.
Abuajwa, O., Hassan, S.M.B.M., Mahmud, A. Bin and Aziz, A.B.A. 2025. Deep Packet Inspection (DPI) Technologies and Their Role in Cyber Threat Detection. In: Multimedia University Engineering Conference (MECON). pp. 1–7. doi: 10.1109/MECON67253.2025.11276900.
Syafi’i Bachtiar, M., Rahaningsih, N. and Dana, R.D. 2024. FIREWALL FILTERING BERBASIS DEEP PACKET INSPECTION DALAM MENDETEKSI DAN MENCEGAH ANCAMAN MALWARE. Jurnal Mahasiswa Teknik Informatika 8(1), pp. 399–405. doi: 10.36040/jati.v8i1.8387.
Sari, D.P., Halim, Z., Irlon, I., Waseso, B. and Saromah, S. 2024. Implementasi Machine Learning untuk Deteksi Intrusi pada Jaringan Komputer. Jurnal Minfo Polgan 13(2), pp. 1389–1394. doi: 10.33395/jmp.v13i2.14074.
Laghrissi, F., Douzi, S., Douzi, K. and Hssina, B. 2021. Intrusion detection systems using long short-term memory (LSTM). Journal of Big Data 8(1), p. 65. doi: 10.1186/s40537-021-00448-4.
Alwhbi, I.A., Zou, C.C. and Alharbi, R.N. 2024. Encrypted Network Traffic Analysis and Classification Utilizing Machine Learning. Sensors 24(11), pp. 1–17. doi: 10.3390/s24113509.
Rahayu Prasiska. 2025. Klasifikasi Traffic Jaringan Online Gambling Berbasis Deep Learning. Skripsi. Sistem Komputer. Universitas Sriwijaya.
Yang, G., Wu, B., He, J., Ni, L. and Xia, T. 2025. Towards Reliable Detection of Malicious DNS-over-HTTPS (DoH) Tunneling Traffic Under Low-Quality Training Data. pp. 423–434. doi: 10.1007/978-981-96-9872-1_35.
Hasin, M., Havrilla, M. and Chovancová, E. 2023. Detection of HTTP DDoS Attacks Using NFStream and TensorFlow. Applied Sciences 13(11), pp. 6665–6671. doi: 10.3390/app13116671.
Correia, L., Goos, J.-C., Klein, P., Bäck, T. and Kononova, A. V. 2025. TeVAE: A Variational Autoencoder Approach for Discrete Online Anomaly Detection in Variable-State Multivariate Time-Series Data. In: Computational Intelligence. Springer Nature Switzerland 1196, pp. 106–132. doi: 10.1007/978-3-031-85252-7_7.
Vasudev Karthik Ravindran, Sharad Shyam Ojha and Arvind Kamboj. 2025. A Comparative Analysis of Signature-Based and Anomaly-Based Intrusion Detection Systems. International Journal of Latest Technology in Engineering Management & Applied Science 14(5), pp. 209–214. doi: 10.51583/IJLTEMAS.2025.140500026.
Karuna Jyothi, K. and Reddy, B.I. 2023. CSEIT1835225 | Study on Virtual Private Network (VPN), VPN’s Protocols And Security Study on Virtual Private Network (VPN), VPN’s Protocols And Security. International Journal of Scientific Research in Computer Science, Engineering and Information Technology 3(5). pp. 919-932 Available at: https://www.researchgate.net/publication/368831275.
Scourfield, M., Saintonge, A., de Mijolla, D. and Viti, S. 2023. De-noising of galaxy optical spectra with autoencoders. Monthly Notices of the Royal Astronomical Society 526(2), pp. 3037–3050. doi: 10.1093/mnras/stad2709.
Domínguez-Morales, M., Civit-Masot, J., Muñoz-Saavedra, L. and Damaševičius, R. 2024. Deep Learning. London: IntechOpen. doi: 10.5772/intechopen.107725.
Eman Jawad. 2023. THE DEEP NEURAL NETWORK-A REVIEW. JOURNAL OF MATHEMATICS 9(9), pp. 1–5. doi: 10.53555/m.v9i9.5842.
Vujovic, Ž.Ð. 2021. Classification Model Evaluation Metrics. International Journal of Advanced Computer Science and Applications 12(6). pp. 599-606. doi: https://dx.doi.org/10.14569/IJACSA.2021.0120670.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Aan Alma Khanafi, Indra Lina Putra, Tutik Khotimah
This work is licensed under a Creative Commons Attribution 4.0 International License.
