A Hybrid Deep Learning Model for Efficient IOT Botnet Attack Detection

Abstract

The rapid growth of the Internet of Things (IoT) has significantly improved connectivity and automation across various domains. However, it has also increased the risk of cyber threats, particularly botnet attacks that compromise connected devices and disrupt network operations. Traditional machine learning techniques often struggle to detect sophisticated and evolving botnet attacks due to the complexity and high-dimensional nature of network traffic. This project proposes a Hybrid Deep Learning Model for Efficient IoT Botnet Attack Detection by integrating Artificial Neural Networks , Convolutional Neural Networks , Long Short-Term Memory, and Recurrent Neural Networks into a stacked ACLR framework. The proposed model leverages the feature extraction capability of CNN, the temporal learning strength of LSTM and RNN, and the classification power of ANN to accurately identify malicious network traffic. The model is trained and evaluated using the UNSW-NB15 dataset after appropriate preprocessing, including data cleaning, normalization, and label encoding. Experimental results demonstrate that the proposed approach achieves high detection accuracy, precision, recall, F1-score, and ROCAUC, outperforming several existing machine learning and deep learning methods. The proposed hybrid framework provides a robust, scalable, and reliable solution for real-time botnet attack detection, enhancing the security and resilience of modern IoT networks against evolving cyber threats.