Pati, Mar’i (2024) Analisa Keakuratan Algoritma NaÏve Bayes, Support Vector Machine (svm), Dan Logistic Regression Untuk Deteksi Malware Pada Trafik Data Iot. Other thesis, Universitas Islam Riau.

Text Mar’i Pati.pdf - Submitted Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

The Internet of Things (IoT) connects various devices such as sensors, cameras, and smart home appliances through networks, providing significant benefits but also increasing the risk of malware attacks. This study aims to analyze the accuracy of three machine learning algorithms—Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression—in detecting malware in IoT network traffic. The dataset used contains information on IoT traffic labeled as either malware or benign. The research methodology includes data collection, preprocessing, categorical feature encoding, data normalization, data splitting, model training, and evaluation using accuracy, precision, recall, and F1-score metrics. The results show that the SVM algorithm has the best performance with the highest accuracy, followed by Logistic Regression and Naïve Bayes. This study provides practical guidance for cybersecurity practitioners in selecting effective algorithms for malware detection and suggests exploring ensemble techniques to improve future accuracy. By better understanding the accuracy and limitations of various algorithms, this research aims to contribute to enhancing the security and integrity of IoT systems.

Actions (login required)

View Item