To read the full version of this content please select one of the options below:

Detection and prevention of black-hole and wormhole attacks in wireless sensor network using optimized LSTM

Mohandas V. Pawar (VIT University, Vellore, India)
Anuradha J. (VIT University, Vellore, India)

International Journal of Pervasive Computing and Communications

ISSN: 1742-7371

Article publication date: 3 June 2021

97

Abstract

Purpose

This study aims to present a novel system for detection and prevention of black hole and wormhole attacks in wireless sensor network (WSN) based on deep learning model. Here, different phases are included such as assigning the nodes, data collection, detecting black hole and wormhole attacks and preventing black hole and wormhole attacks by optimal path communication. Initially, a set of nodes is assumed for carrying out the communication in WSN. Further, the black hole attacks are detected by the Bait process, and wormhole attacks are detected by the round trip time (RTT) validation process. The data collection procedure is done with the Bait and RTT validation process with attribute information. The gathered data attributes are given for the training in which long short-term memory (LSTM) is used that includes the attack details. This is used for attack detection process. Once they are detected, those attacks are removed from the network using the optimal path selection process. Here, the optimal shortest path is determined by the improvement in the whale optimization algorithm (WOA) that is called as fitness rate-based whale optimization algorithm (FR-WOA). This shortest path communication is carried out based on the multi-objective function using energy, distance, delay and packet delivery ratio as constraints.

Design/methodology/approach

This paper implements a detection and prevention of attacks model based on FR-WOA algorithm for the prevention of attacks in the WSNs. With this, this paper aims to accomplish the desired optimization of multi-objective functions.

Findings

From the analysis, it is found that the accuracy of the optimized LSTM is better than conventional LSTM. The energy consumption of the proposed FR-WOA with 35 nodes is 7.14% superior to WOA and FireFly, 5.7% superior to grey wolf optimization and 10.3% superior to particle swarm optimization.

Originality/value

This paper develops the FR-WOA with optimized LSTM detecting and preventing black hole and wormhole attacks from WSN. To the best of the authors’ knowledge, this is the first work that uses FR-WOA with optimized LSTM detecting and preventing black hole and wormhole attacks from WSN.

Keywords

Citation

Pawar, M.V. and J., A. (2021), "Detection and prevention of black-hole and wormhole attacks in wireless sensor network using optimized LSTM", International Journal of Pervasive Computing and Communications, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/IJPCC-10-2020-0162

Publisher

:

Emerald Publishing Limited

Copyright © 2021, Emerald Publishing Limited

Related articles