Title: Deep learning algorithms providing security for wireless sensor networks against malicious attacks

Authors: Dinokumar Kongkham

Addresses: Department of Electronics and Communication Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Science (SIMATS), Saveetha University, Chennai, Tamil Nadu, India

Abstract: Small sensor nodes that have limited energy are the building blocks of wireless sensor networks, often known as WSNs. WSNs are self-sufficient and space-distributed. A WSN is vulnerable to security concerns because it lacks a central authority and deploys its nodes in a random fashion across the network. A malicious assault is a well-known kind of attack in WSN. This type of attack involves a hacked node impersonating as one of the network nodes and fooling other nodes. Either via the use of cryptographic techniques or by the synchronisation of time, a variety of strategies are created to defend against these attacks. However, due to the autonomous nature of WSNs, these strategies may not be successful. To protect against malicious assaults, this article presents a technique that is both effective and efficient, which is known as the Hamming Residue Method (HRM).

Keywords: deep learning; security; WSN; wireless sensor network; malicious attacks.

DOI: 10.1504/IJIPT.2024.143761

International Journal of Internet Protocol Technology, 2024 Vol.17 No.1, pp.1 - 8

Received: 04 Nov 2023
Accepted: 08 Jun 2024
Published online: 06 Jan 2025 *