Klasifikasi Malicious Websites Menggunakan Algoritma K-NN Berdasarkan Application Layers dan Network Characteristics
DOI:
https://doi.org/10.31154/cogito.v4i1.100.37-45Abstract
Dalam kehidupan di era teknologi sekarang ini semua aktivitas manusia telah dipengaruhi oleh internet. Berbagi informasi, komunikasi, sosialisasi, berbelanja, berbisnis, pendidikan dan banyak hal lainnya yang dapat dilakukan menggunakan internet. Seiring dengan berkembangnya internet berbagai macam ancaman keamanan menjadi lebih beragam. Virus adalah musuh nomor satu di internet. Virus memanfaatkan berbagai metode untuk dapat menghindari anti-virus, salah satunya adalah Malware. Malware adalah salah satu kode berbahaya yang dapat mengubah, merusak dan mencuri data pribadi yang dapat merugikan individual ataupun kelompok. Penelitian ini akan memprediksi malicious website berdasarkan application layer dan network characteristics menggunakan metode K-Nearest Neighbor. Penelitian ini menggunakan metode data cleaning dan data reduction untuk data preprocessing, dan feature selection untuk pemilihan attribut yang paling berpengaruh pada malicious website. Untuk memprediksi malicious website penulis menggunakan algoritma K-NN dengan hasil 2,42% precision lebih tinggi dibandingkan dengan penelitian sebelumnya yang menggunakan algoritma Naïve Bayes. Keywords : Klasifikasi, Network Characteristics, Malicious Websites, Application Layers, K-NN, Naïve BayesReferences
J. Milan and P. Bajaj, "Techniques in Detection and Analyzing Malware Executebles: A Review," International Journal of Computer Science and Mobile Computing, vol. 13, no. 5, p. 930, 2014.
A. Retno and L. A. Novarina, "Malware Dynamic," Jurnal of Education and Information Communication Tecnology, vol. 1, no. 1, p. 37, 2017.
D. A. K. Dutta, "Detection of Malware and Malicious Executables Using E-Birch Algorithm," International Journal of Advanced Computer Science and Applications, vol. 7, no. 1, p. 124, 2016 .
"Technopedia," [Online]. Available: https://www.techopedia.com/definition/6006/application-layer. [Accessed 7 May 2018].
A. Altaher, "Phising Website Classification using Hybrid SVM and KNN Approach" International Journal of Advanced Computer Science and Applications, vol. 8, no.6, 2017.
M. Aldwairi and R. Alsalman, "Malurls: A Lightweight Malicious Website," Journal Of Emerging Technologies In Web Intelligence, vol. 4, no. 2, 2012.
"Kaggle," [Online]. Available: https://www.kaggle.com/xwolf12/malicious-and-benign-websites. [Accessed 12 April 2018].
"OpenML," [Online]. Available: https://www.openml.org/a/estimation-procedures/1. [Accessed 20 April 2018].
S. B. Imandoust and M. Bolandraftar, "Application of K-Nearest Neighbor (KNN) Approach for Predicting Economic Events: Theoretical Background," S B Imandoust et al. Int. Journal of Engineering Research and Applications, vol. 3, no. 5, 2013.
M. Bramer, "Principles of data mining," Springer, 2007.
A. T. Liem, G. A. Sandag, I.-S. Hwang and A. Nikoukar, "Delay analysis of dynamic bandwidth allocation for triple-play-services in EPON," 2017.
B. Sui, "Information Gain Feature Selection Based On Feature Interactions," 2013.
C. Urcuqui, A. Navarro, J. Osorio and M. Garcia, "Machine Learning Classifiers to Detect Malicious Websites," CEUR Workshop Proceedings, vol. 1950, pp. 14-17, 2017.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).