Analisis Penerapan Deep Learning untuk Klasifikasi Serangan Terhadap Keamanan Jaringan
Abstract
The growth of the information technology field necessitates newer and better methods for data and information security. Several methods in machine learning are tried to be applied to network security mechanisms. Classical methods in network security use the identification of traffic or network traffic as a critical component in detecting attacks. This mechanism becomes increasingly ineffective as the network scales and data usage increases. One of the solutions to overcome the increase in size and data is deep learning. This type of machine learning method used in security can perform extensive data analysis and is a recent innovation that tries to study information patterns to detect unauthorized entries into computer networks. This study tries to conduct a preliminary study to apply Deep Learning to classify network security attacks originating from attack datasets. Based on the trials conducted, Deep learning can classify attacks with good accuracy according to the Deep learning architectural model used.
Keywords: Network Security Classification Deep Learning Machine Learning
Pertumbuhan bidang teknologi informasi mengharuskan perlunya metode yang lebih baru dan lebih baik untuk keamanan data dan informasi. Terdapat beberapa metode dalam pembelajaran mesin yang dicoba diterapkan untuk mekanisme pengaman jaringan. Metode klasik dalam keamanan jaringan menggunakan identifikasi lalu lintas atau trafik jaringan sebagai komponen kunci dalam mendeteksi serangan. Mekanisme ini semakin menjadi tidak efektif karena peningkatan skala jaringan dan penggunaan data. Solusi mengatasi peningkatan ukuran dan data salah satunya dengan Deep learning. Jenis metode pembelajaran mesin ini digunakan dalam keamanan dapat melakukan analisis data dalam ukuran besar dan merupakan inovasi terbaru yang mencoba mempelajari pola informasi dengan tujuan mendeteksi entri yang tidak sah ke dalam jaringan komputer. Penelitian ini mencoba melakukan studi awal untuk menerapkan Deep Learning untuk klasifikasi serangan keamanan jaringan yang berasal dari dataset serangan. Berdasarkan ujicoba yang dilakukan Deep learning dapat melakukan klasifikasi serangan dengan akurasi yang baik sesuai dengan model arsitektur Deep learning yang digunakan.
Kata kunci: Keamanan Jaringan, Klasifikasi, Deep Learning, Mesin Learning
Full Text:
PDFReferences
Q. Niyaz, W. Sun, A. Y. Javaid dan A. Mansoor, “A Deep Learning Approach for Network Intrusion Detection System,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 02, no. 01, pp. 41 - 50, 2018.
B. P. Firdaus dan I. M. Suartana, “Implementasi Keamanan Jaringan Intrusion Detection/Prevention System Menggunakan Pfsense,” Jurnal Manajemen Informatika, vol. 11, no. 1, pp. 40-47, 2020.
B. Doong dan X. Wang, “Comparison Deep Learning Method to Traditional Methods Using for Network Intrusion Detection,” dalam 8th IEEE International Conference on Communication Software and Networks, Beijing, 2016.
R. Pascanu, J. Stokes, H. Sanossian dan M. Marinesc, “Malware classification with recurrent networks,” dalam IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015.
M. A. S. F. E. A. R. D. E. Hassanien, “Hybrid Intelligent Intrusion Detection Scheme,” dalam Soft Computing in Industrial Applications, Springer, Berlin, Heidelberg, 2011.
F. P. A. C. A. D. S. U. Fiore, “Network anomaly detection with the restricted boltzmann machine,” dalam Neurocomputing, 2013.
S. Mahdavifar dan A. A. Ghorbani, “Application of Deep Learning to Cybersecurity: A Survey,” Neurocomputing, vol. 347, pp. 149-176, 2019.
B. Kolosnjaji, A. Zarras dan G. WebsterClau, “Deep Learning for Classification of Malware System Call Sequences,” dalam Australasian Joint Conference on Artificial Intelligence, New Zealand , 2016.
M. Tavallaee, E. Bagheri, W. Lu dan A. A. Ghorbani, “A detailed analysis of the KDD CUP 99 data set,” dalam 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, Canada, 2009.
M. . L. Kristy, B. J. Trevor, B. W. Kenneth dan D. E. Thomas, “Feature extraction and feature selection for classifying cyber traffic threats,” Journal of Defense Modeling and Simulation: Applications, Methodology, Technology, vol. 14, no. 3, p. 217–231, 2017.
T.-T. Wong, “Linear Approximation of F-Measure for the Performance Evaluation of Classification Algorithms on Imbalanced Data Sets,” IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 2, pp. 753 - 763, 2022.
DOI: http://dx.doi.org/10.20527/klik.v9i1.451
Copyright (c) 2022 KLIK - KUMPULAN JURNAL ILMU KOMPUTER
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License. View My Stats