IMPLEMENTATION OF NAÏVE BAYES ALGORITHM BASED ON PARTICLE SWARM OPTIMIZATION FOR INTRUSION DETECTION SYSTEM (IDS)
Article Sidebar
Main Article Content
Abstract
Intrusion Detection System (IDS) is an important mechanism in detecting suspicious activity on computer networks, including intrusion attempts that have the potential to threaten data security. This study aims to analyze the application of the Naïve Bayes algorithm optimized with Particle Swarm Optimization (PSO) in the classification of network attacks using the KDD Cup 1999 dataset . The research stages include data collection, cleaning, attribute selection, transformation, modeling, and evaluation using RapidMiner Studio software. The Naïve Bayes algorithm was chosen because of its simplicity and efficiency in classifying large data, while PSO optimization was applied to improve the accuracy of the classification results. Performance evaluation was carried out with a confusion matrix through accuracy, precision, and recall metrics . The test results showed that the model produced an accuracy rate of 95.00%, a recall of 98.08%, and a precision of 92.73%. These findings prove that the integration of Naïve Bayes and PSO can improve the performance of IDS in detecting attacks with a lower error rate. The practical implication of this research is the availability of an effective computational approach to support cyber attack prevention strategies, while contributing to the development of more adaptive network security systems.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
M. Khudadad and Z. Huang, “Intrusion Detection with Tree-Based Data Mining Classification Techniques by Using KDD,” Lect. Notes Inst. Comput. Sci. Soc. Telecommun. Eng. LNICST, vol. 227 LNICST, no. 6, pp. 294–303, 2018, doi: 10.1007/978-3-319-73447-7_33.
INT Wirawan and I. Eksistyanto, “Application of Naive Bayes in Intrusion Detection System with Variable Discretization,” JUTI J. Ilm. Teknol. Inf., vol. 13, no. 2, p. 182, 2015, doi: 10.12962/j24068535.v13i2.a487.
L. Dhanabal and SP Shantharajah, “A Study on NSL-KDD Dataset for Intrusion Detection System Based on Classification Algorithms,” Int. J. Adv. Res. Comput. Commun. Eng., vol. 4, no. 6, pp. 446–452, 2015, doi: 10.17148/IJARCCE.2015.4696.
Jupriyadi, “Implementation of Feature Selection Using the FVBRM Algorithm for Attack Classification in Intrusion Detection Systems (IDs),” Semin. Nas. Teknol. Inf., vol. 17, no. January 2018, pp. 1–6, 2018.
N. Rosli et al., “Jurnal Teknologi,” vol. 1, pp. 1–6, 2015.
G. Wang et al., “No Title大学生の職業未決定の研究,” Appl. Catal. A Gen., vol. 58, no. 2, pp. 15–22, 2013, doi: 10.1179/1743280412Y.0000000001.
H. Tiaield, "Data Mining Based Cyber-Attack Detection," Univ. Glas., vol. 13, no. 2, pp. 90–104, 2017, doi: 10.1063/1.2975179.
M. Surahman et al., “APPLICATION OF SVM-BASED MACHINE LEARNING METHOD FOR,” pp. 196–206, 2020.
I. Rahmadani, HS Tambunan, and IS Damanik, “Application of Data Mining in Cities Based on Provinces Responsive to Narcotics Threats Using K-Medoids,” vol. 2, pp. 93–99, 2020.
G. Widi N. Dicky Nofriansyah, Data Mining Algorithms and Testing. Yogyakarta: CV Budi Utama, 2015. Suyanto, Data
a Mining. Yogyakarta: Informatika, 2017.
O. Villacampa, “(Weka - Thesis) Feature Selection and Classification Methods for Decision Making: A Comparative Analysis,” ProQuest Diss. Theses, no. 63, p. 188, 2015.
Retno Tri Vulandari, Data Mining. Yogyakarta: Gava Media, 2017.
Y. Silalahi, Kristiani Silalahi., Murfi, Hendri., Satria, “Comparative Study of Feature Selection for Support Vector Machine in Credit Risk Assessment Classification,” vol. 1, no. 2, pp. 119–136, 2017.