Analisis dan Deteksi Traffic Malware Pada Jaringan Iot Menggunakan Algoritma K-Nearest Neighbor Berbasis Dataset IOT-23

Abstrak

The rapid growth of Internet of Things (IoT) technology has significantly increased the number of connected devices, which also raises security concerns in network environments. IoT devices are often vulnerable due to limited computational resources and weak security mechanisms, making them potential targets for cyberattacks such as malware and Distributed Denial of Service (DDoS). This study aims to analyze malware traffic characteristics and evaluate the performance of the K-Nearest Neighbor (KNN) algorithm in detecting malicious traffic using the IoT-23 dataset. The research adopts a supervised machine learning approach with preprocessing steps including data cleaning, normalization, and feature encoding. The dataset is transformed into binary classification (benign and malicious). Experimental results show that the KNN algorithm achieves high performance with accuracy above 99% across various K values. The best performance is obtained at K=3 with excellent precision, recall, and F1-score. The ROC-AUC value of 0.9937 indicates strong discrimination capability. These results demonstrate that KNN is effective for intrusion detection in IoT environments based on network flow data.