Enhanced DOS Attack Detection System in WSNs using Hybrid Model

Ramezani, Somayeh and Sadri, Seyed Mahdi and Mahmoud, Haitham and Elmitwally, Nouh (2024) Enhanced DOS Attack Detection System in WSNs using Hybrid Model. In: The 4th International Conference of Advanced Computing and Informatics, 16 - 17 December 2024, Birmingham City University. (In Press)

Text
Nouh_Somayeh.pdf - Accepted Version
Restricted to Repository staff only
Download (283kB) | Request a copy

Abstract

Wireless Sensor Networks (WSNs) are fundamental to Next-generation Wire-less systems, facilitating real-time data collection and analysis in diverse fields such as environmental monitoring, building automation, traffic man-agement, and healthcare. However, their decentralized architecture and lim-ited resources make WSNs particularly vulnerable to Denial-of-Service (DoS) attacks, which can severely disrupt network operations. Ensuring the security and reliability of these networks necessitates robust detection mech-anisms for such threats. Hence, this study develops a hybrid model to en-hance the detection of DoS attacks in WSNs. Utilizing the widely-recognized WSN-BFSF dataset, which contains labelled instances of network activity and various types of DoS attacks, we compare multiple detection approach-es. After extensive preprocessing, we implement both traditional and hybrid models, achieving an exceptional accuracy rate of 99.998\% with the J48 al-gorithm. The results demonstrate the superiority of the hybrid approach over the literature review by 0.1\%, offering significant improvements in the early detection and mitigation of DoS attacks in WSNs.

Item Type:	Conference or Workshop Item (Paper)
Dates:	Date Event 16 December 2024 Accepted
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions:	Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User:	Nouh Elmitwally
Date Deposited:	13 Feb 2025 12:52
Last Modified:	13 Feb 2025 12:52
URI:	https://www.open-access.bcu.ac.uk/id/eprint/16134