Detecting LDoS in NB-IoTs by using metaheuristic-based CNN. (22nd June 2021)

• Record Type: Journal Article
• Authors: Chen, Chi-Yuan; Cho, Hsin-Hung; Tsai, Min-Yan; Hann, Augustine Sii Ho; Chao, Han-Chieh
• Is Part Of: International journal of ad hoc and ubiquitous computing. Volume 37:Number 2(2021)
• Page Start: 74
• Page End: 84
• Publication Date: 2021-06-22
• Subjects: narrow band internet of things -- NB-IoT -- intrusion detection system -- IDS -- deep learning -- heuristic algorithm; Ubiquitous computing -- Periodicals; Embedded computer systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Wireless communication systems -- Periodicals; Computer architecture -- Periodicals; 004.2
• Languages: English
• ISSNs: 1743-8225

Abstract

The number of IoT devices will grow explosively due to great potential of the NB-IoT so that the IoT network environment will become a hotbed of botnets. Various IoT devices and platforms will be threatened by DoS attacks. However, NB-IoT has the characteristics of lower speed so it is not an ideal environment for heavy traffic DoS attacks. Low-rate DoS is the main attack method in the NB-IoT environment. In this environment, the attacker can hide the attack packet for avoiding detection in a data stream so that the difficulty of detection will be increased greatly. There are already many CNN methods to identify the characteristics of this attack. However, these traditional methods will cause the amount of data to be insufficiently diverse. In order to improve the phenomenon of overfitting, this article uses simulated annealing to adjust the weight of the CNN to achieve better global search.