EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Approach for Detecting Attacks on IoT Networks Based on Ensemble Feature Selection and Deep Learning Models

Shaza Dawood Ahmed Rihan, Mohammed Anbar iD, Basim Ahmad Alabsi

Sensors · 23.08.2023 · 23 (17) · 7342

DOI: 10.3390/s23177342 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.08.2023. Verfasst von Shaza Dawood Ahmed Rihan und 2 weiteren Autor:innen. Beteiligte Einrichtung: Applied College, Najran University, King Abdulaziz Street, Najran P.O. Box 1988, Saudi Arabia. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Najran University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Internet of Things (IoT) has transformed our interaction with technology and introduced security challenges. The growing number of IoT attacks poses a significant threat to organizations and individuals. This paper proposes an approach for detecting attacks on IoT networks using ensemble feature selection and deep learning models. Ensemble feature selection combines filter techniques such as variance threshold, mutual information, Chi-square, ANOVA, and L1-based methods. By leveraging the strengths of each technique, the ensemble is formed by the union of selected features. However, this union operation may overlook redundancy and irrelevance, potentially leading to a larger feature set. To address this, a wrapper algorithm called Recursive Feature Elimination (RFE) is applied to refine the feature selection. The impact of the selected feature set on the performance of Deep Learning (DL) models (CNN, RNN, GRU, and LSTM) is evaluated using the IoT-Botnet 2020 dataset, considering detection accuracy, precision, recall, F1-measure, and False Positive Rate (FPR). All DL models achieved the highest detection accuracy, precision, recall, and F1 measure values, ranging from 97.05% to 97.87%, 96.99% to 97.95%, 99.80% to 99.95%, and 98.45% to 98.87%, respectively.

Schlagwörter

Stichwörter der Autor:innen

Internet of ThingsIoT attacksIoT-Botnet 2020 datasetRecursive Feature Elimination (RFE)deep learning modelsensemble feature selection

Autor:innen und Institutionen

  • Applied College, Najran University, King Abdulaziz Street, Najran P.O. Box 1988, Saudi Arabia.
  • National Advanced IPv6 (NAv6) Centre, Universiti Sains Malaysia (USM), Gelugor 11800, Penang, Malaysia.

ORCID-Profile: Mohammed Anbar

Förderung

  • Najran University

Zitieren

APA

Rihan, S. D. A., Anbar, M., & Alabsi, B. A. (2023). Approach for Detecting Attacks on IoT Networks Based on Ensemble Feature Selection and Deep Learning Models. Sensors, 23(17), 7342. https://doi.org/10.3390/s23177342

Vancouver

Rihan SDA, Anbar M, Alabsi BA. Approach for Detecting Attacks on IoT Networks Based on Ensemble Feature Selection and Deep Learning Models. Sensors. 2023;23(17):7342. doi:10.3390/s23177342

BibTeX
@article{Rihan2023,
  author = {Rihan, Shaza Dawood Ahmed and Anbar, Mohammed and Alabsi, Basim Ahmad},
  title = {Approach for Detecting Attacks on IoT Networks Based on Ensemble Feature Selection and Deep Learning Models},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {17},
  pages = {7342},
  doi = {10.3390/s23177342}
}
Kostenlos starten →