Your browser doesn't support javascript.
loading
A secure worst elite sailfish optimizer based routing and deep learning for black hole attack detection.
Kumar, Mandeep; Ali, Jahid.
Afiliação
  • Kumar M; Department of Computer Science & Engineering, I.K. Gujral Punjab Technical University, Kapurthala, India.
  • Ali J; Department of Computer Applications, Sri Sai Iqbal College of Management and Information Technology, Pathankot, India.
Network ; : 1-26, 2024 Jun 10.
Article em En | MEDLINE | ID: mdl-38855986
ABSTRACT
The Wireless Sensor Network (WSN) is susceptible to two kinds of attacks, namely active attack and passive attack. In an active attack, the attacker directly communicates with the target system or network. In contrast, in passive attack, the attacker is in indirect contact with the network. To preserve the functionality and dependability of wireless sensor networks, this research has been conducted recently to detect and mitigate the black hole attacks. In this research, a Deep learning (DL) based black hole attack detection model is designed. The WSN simulation is the beginning stage of this process. Moreover, routing is the key process, where the data is passed to the base station (BS) via the shortest and finest route. The proposed Worst Elite Sailfish Optimization (WESFO) is utilized for routing. Moreover, black hole attack detection is performed in the BS. The Auto Encoder (AE) is employed in attack detection, which is trained with the use of the proposed WESFO algorithm. Additionally, the proposed model is validated in terms of delay, Packet Delivery Rate (PDR), throughput, False-Negative Rate (FNR), and False-Positive Rate (FPR) parameters with the corresponding outcomes like 25.64 s, 94.83%, 119.3, 0.084, and 0.135 are obtained.
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Revista: Network Assunto da revista: NEUROLOGIA Ano de publicação: 2024 Tipo de documento: Article País de afiliação: Índia

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Revista: Network Assunto da revista: NEUROLOGIA Ano de publicação: 2024 Tipo de documento: Article País de afiliação: Índia