A Survey of Quantitative Comparative Research on Intrusion Detection Algorithms in Wireless Sensor Networks
Yahong Yang, Pan Wang, Zixuan Wang, Zeyi Li · 2022 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · 2022
Wireless Sensor Network (WSN) is vulnerable to malicious attacks by third parties due to limited communication capabilities and unstable channels. Moreover, WSN nodes have limited energy, small storage space, and poor computing power, which restrict traditional intrusion detection methods. In recent years, people have tried to apply many traditional intrusion detection algorithms to WSN. Meanwhile, experimental results compared several intrusion detection algorithms. However, the experimental comparison of these intrusion detection algorithms is not comprehensive enough. Deep Forest and ELM algorithms are not considered. Therefore, this paper evaluates eight intrusion detection algorithms on four datasets and details the selection of algorithms, datasets, and evaluation indicators. The final experimental results show that the comprehensive performance of Deep Forest on WSN is better. The intrusion detection algorithm research in this paper provides more ideas.