Memory-Efficient Deep Learning for Botnet Attack Detection in IoT Networks

Electronics

Mohammad Hammoudeh¹  AderemiA. Atayero²  SegunI. Popoola³  Bamidele Adebisi³  Ruth Ande³ 

[1] Department of Computing and Mathematics, Manchester Metropolitan University, Manchester M1 5GD, UK;Department of Electrical and Information Engineering, Covenant University, Ota P.M.B. 1023, Nigeria;Department of Engineering, Manchester Metropolitan University, Manchester M1 5GD, UK;

关键词: botnet;    cybersecurity;    machine learning;    deep learning;    intrusion detection;    network traffic;   

DOI  :  10.3390/electronics10091104

来源: DOAJ

【 摘 要 】

Cyber attackers exploit a network of compromised computing devices, known as a botnet, to attack Internet-of-Things (IoT) networks. Recent research works have recommended the use of Deep Recurrent Neural Network (DRNN) for botnet attack detection in IoT networks. However, for high feature dimensionality in the training data, high network bandwidth and a large memory space will be needed to transmit and store the data, respectively in IoT back-end server or cloud platform for Deep Learning (DL). Furthermore, given highly imbalanced network traffic data, the DRNN model produces low classification performance in minority classes. In this paper, we exploit the joint advantages of Long Short-Term Memory Autoencoder (LAE), Synthetic Minority Oversampling Technique (SMOTE), and DRNN to develop a memory-efficient DL method, named LS-DRNN. The effectiveness of this method is evaluated with the Bot-IoT dataset. Results show that the LAE method reduced the dimensionality of network traffic features in the training set from 37 to 10, and this consequently reduced the memory space required for data storage by $86.49\%$. SMOTE method helped the LS-DRNN model to achieve high classification performance in minority classes, and the overall detection rate increased by $10.94\%$. Furthermore, the LS-DRNN model outperformed state-of-the-art models.

【 授权许可】

Unknown