Botnet Attack Detection and Mitigation Based on Iot Networks

Abstract

The rapid growth of the Internet of Things (IoT) has increased the use of smart devices in applications such as healthcare, smart homes, industrial automation, and transportation. However, limited security mechanisms and resource constraints make IoT devices highly vulnerable to cyber threats, particularly botnet attacks. Botnet attacks compromise connected devices and use them to perform malicious activities such as Distributed Denial of Service (DDoS), malware propagation, unauthorized access, and data theft, resulting in serious security and network performance issues. Traditional intrusion detection systems often fail to detect evolving botnet attacks because of complex traffic behavior and dynamic attack patterns. This research proposes a hybrid botnet attack detection and mitigation framework for IoT networks using Random Forest, XGBoost, and Long Short-Term Memory (LSTM). In the proposed model, Random Forest is used for feature selection, XGBoost improves attack classification, and LSTM captures sequential traffic behavior for better detection of hidden attack patterns. The framework is evaluated using the N-BaIoT benchmark dataset with performance metrics such as accuracy, precision, recall, F1-score, and false positive rate. Experimental results show that the proposed hybrid model improves botnet detection accuracy, reduces false alarms, and enhances mitigation capability compared with traditional approaches. The proposed framework provides an intelligent and reliable security solution for protecting IoT networks against botnet attacks.