Open AccessIFACNN: efficient DDoS attack detection based on improved firefly algorithm to optimize convolutional neural networks
Author(s) -
Jiushuang Wang,
AUTHOR_ID,
Ying Liu,
Huifen Feng
Publication year - 2021
Publication title -
mathematical biosciences and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.451
H-Index - 45
eISSN - 1551-0018
pISSN - 1547-1063
DOI - 10.3934/mbe.2022059
Subject(s) - denial of service attack , computer science , trinoo , application layer ddos attack , internet of things , computer network , convolutional neural network , scheme (mathematics) , computer security , software defined networking , software , firefly algorithm , network security , the internet , algorithm , artificial intelligence , world wide web , mathematical analysis , mathematics , particle swarm optimization , programming language
Network security has become considerably essential because of the expansion of internet of things (IoT) devices. One of the greatest hazards of today's networks is distributed denial of service (DDoS) attacks, which could destroy critical network services. Recent numerous IoT devices are unsuspectingly attacked by DDoS. To securely manage IoT equipment, researchers have introduced software-defined networks (SDN). Therefore, we propose a DDoS attack detection scheme to secure the real-time in the software-defined the internet of things (SD-IoT) environment. In this article, we utilize improved firefly algorithm to optimize the convolutional neural network (CNN), to provide detection for DDoS attacks in our proposed SD-IoT framework. Our results demonstrate that our scheme can achieve higher than 99% DDoS behavior and benign traffic detection accuracy.