Implementasi Metode K-Medoids Untuk Masalah Intrusion Detection System Menggunakan Bahasa Pemrograman Matlab

Octaviani Hutapea(1*), Aini Suri Talita(2)

(1) 
(2) Gunadarma University
(*) Corresponding Author

Abstract


Based on data from the National Cyber And Crypto Agency (BSSN) of the Republic of Indonesia from 2018 to 2021, the threat of cyber attacks continues to experience a significant increase. In 2021, a significant change that is likely to be faced is with the emergence of new smart devices, which are more than just end-users and remotely connected networked devices. Surely, gives it the attention of all parties. There are many types of cyberattacks including Malware, Phishing, Ransomeware, etc. IDS (Intrusion Detection System) is a method that can detect suspicious activity in a system or network. Implementation of the Fuzzy K-Medoids method by using the Matlab programming language that retrieves data from KDDCUP’99 which has been normalized. The data used are normal data and anomaly attack data which are categorized as DoS, Probe, R2L, and U2R. From the research conducted the accuracy percentage is around 60-89% with three types of data preprocessing

Full Text:

PDF (Indonesian)

References


N. P. K. S. Kadam, S. B. Bagal, Y. S. Thakare and Sonawane, “Canberra Distance Metric Based Hyperline Segment Pattern Classifier Using Hybrid Approach of Fuzzy Logic and Neural Network,” 2014, pp. 28–30.

H. Moudni, M. Er-rouidi, H. Mouncif, and B. El Hadadi, “Fuzzy logic based intrusion detection system against black hole attack in mobile ad hoc networks,” Int. J. Commun. Networks Inf. Secur., vol. 10, no. 2, pp. 366–373, 2018.

Wu TM, Intrusion Detection Systems Information Assurance Tools Report Sixth Edition September 25, Sixth. Information Assurance Technology Analysis Center, 2018.

M. Moorthy and S. Sathiyabama, “Hybrid fuzzy based intrusion detection system for wireless local area networks,” Eur. J. Sci. Res., vol. 53, no. 3, pp. 431–446, 2011.

A. Shah, S. Clachar, M. Minimair, and D. Cook, “Building multiclass classification baselines for anomaly-based network intrusion detection systems,” 2020, doi: 10.1109/DSAA49011.2020.00102.

C. M. Ou, “Host-based Intrusion Detection Systems Inspired by Machine Learning of Agent-Based Artificial Immune Systems,” 2019, doi: 10.1109/INISTA.2019.8778269.

L. Kaufman and P. E. Rousseeuw, “Clustering by means of Medoids,” Statistical Data Analysis Based on the L1 Norm and Related Methods. 1987.

K. G. Soni and A. Patel, “Comparative Analysis of K-means and K-medoids Algorithm on IRIS Data,” 2017.

M. K. Siddiqui and S. Naahid, “Analysis of KDD CUP 99 Dataset using Clustering based Data Mining,” Int. J. Database Theory Appl., vol. 6, no. 5, pp. 23–34, 2013, doi: 10.14257/ijdta.2013.6.5.03.

S. Devaraju and S. Ramakrishnan, “Detection of Accuracy for Intrusion Detection System Using Neural Network Classifier,” Int. J. Emerg. Technol. Adv. Eng., vol. 3, no. 1, pp. 338–345, 2013.

B. Bansal, “International Journal of Advanced Research in Computer Science and Software Engineering Rule Based Intrusion Detection System to Identify Attacking Behaviour and Severity of Attacks,” vol. 5, no. 1, pp. 718–724, 2015.

A. Suri Talita and E. Prasetyo Wibowo, “Intrusion Detection Systems Data Classification by Possibilistic C-Means Method,” J. Eng. Appl. Sci., vol. 15, no. 5, pp. 1170–1174, 2019, doi: 10.36478/jeasci.2020.1170.1174.




DOI: http://dx.doi.org/10.30998/faktorexacta.v14i2.9429

Refbacks



Bookmark and Share


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

DOAJ faktor exacta Garuda ISSN BRIN sinta

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

Flag Counter

site stats View Faktor Exacta Stats


pkp index