Intrusion Detection Systems in Wireless Sensor Networks Using AI & ML
International Journal of Emerging Knowledge Studies · 30.03.2026 · 5 (03) · 454-462
DOI: 10.70333/ijeks-05-03-017 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Emerging Knowledge Studies, online erschienen am 30.03.2026. Verfasst von Prashant Kumar und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Wireless Sensor Networks (WSNs) have found numerous applications in fields like environment monitoring, healthcare systems, smart cities, and industrial automation. However, WSNs are susceptible to many kinds of cyber security attacks such as denial-of-service attacks, sinkhole attacks, wormhole attacks and selective forwarding attack because of their distributed architecture, limited computational resources, and wirelesscommunication channels. But it does not help you identify what is bad for a network, how to protect the integrity of your network! Machine Learning (ML) and Artificial Intelligence (AI) techniques have become one of the efficient tools in detecting complex intrusion patterns, during recent years. This research paper provides an overview of various AI and ML-based intrusion detection approaches in WSN domain. This study provides a comprehensive review of different detection approaches such as supervised learning algorithms, unsupervised learning techniques, deep learning methods, and hybrid detection systems. Also, it discusses widely used datasets, feature extraction methods and popular performance measures which include accuracy, precision, recall, F1 score and false positive rate. Moreover, the review highlights and compares pros and cons of several potential machine learning algorithms employed for intrusion detection in resource constrained sensor networks. In addition, this paper showcases specific research challenges such as energy consumption, dataset imbalance, distributed detection methods and model explainability. Finally, this paper identifies potential future research directions to improve the efficiency and scalability of intrusion detection systems (IDS) for next-generation WSNs, including lightweight deep learning models, federated learning, edge intelligence and explainable artificial intelligence.
Zitieren
APA
Kumar, P., Gupta, D. D. K., & Garg, S. (2026). Intrusion Detection Systems in Wireless Sensor Networks Using AI & ML. International Journal of Emerging Knowledge Studies, 5(03), 454-462. https://doi.org/10.70333/ijeks-05-03-017
Vancouver
Kumar P, Gupta DDK, Garg S. Intrusion Detection Systems in Wireless Sensor Networks Using AI & ML. International Journal of Emerging Knowledge Studies. 2026;5(03):454-462. doi:10.70333/ijeks-05-03-017
BibTeX
@article{Kumar2026,
author = {Kumar, Prashant and Gupta, Dr. Deepak Kumar and Garg, Shweta},
title = {Intrusion Detection Systems in Wireless Sensor Networks Using AI & ML},
journal = {International Journal of Emerging Knowledge Studies},
year = {2026},
volume = {5},
number = {03},
pages = {454--462},
doi = {10.70333/ijeks-05-03-017}
}
EUVIMED