A Novel Hybrid Intrusion Detection System (IDS) for the Detection of Internet of Things (IoT) Network Attacks

Annals of Emerging Technologies in Computing

article

Ramadan, Rabie A.¹  Yadav, Kusum¹ 

[1] Computer Science and Engineering College, University of Hai’l;Computer Engineering Department, Cairo University

关键词: IoT;    Hybrid classification;    IoT security;    Convolution Neural Network;    KDD cup dataset;   

DOI  :  10.33166/AETiC.2020.05.004

学科分类：电子与电气工程

来源: International Association for Educators and Researchers (IAER)

【 摘 要 】

Nowadays, IoT has been widely used in different applications to improve the quality of life. However, the IoT becomes increasingly an ideal target for unauthorized attacks due to its large number of objects, openness, and distributed nature. Therefore, to maintain the security of IoT systems, there is a need for an efficient Intrusion Detection System (IDS). IDS implements detectors that continuously monitor the network traffic. There are various IDs methods proposed in the literature for IoT security. However, the existing methods had the disadvantages in terms of detection accuracy and time overhead. To enhance the IDS detection accuracy and reduces the required time, this paper proposes a hybrid IDS system where a preprocessing phase is utilized to reduce the required time and feature selection as well as the classification is done in a separate stage. The feature selection process is done by using the Enhanced Shuffled Frog Leaping (ESFL) algorithm and the selected features are classified using Light Convolutional Neural Network with Gated Recurrent Neural Network (LCNN-GRNN) algorithm. This two-stage method is compared to up-todate methods used for intrusion detection and it over performs them in terms of accuracy and running time due to the light processing required by the proposed method.

【 授权许可】

CC BY