Integrating Deep Learning with IOT: Combined Strategies for Botnet Detection
SMART MOVES JOURNAL IJOSCIENCE · 2024
DOI: 10.24113/ijoscience.v10i9.487 ↗Kurz gefasst
Fachartikel in der Zeitschrift SMART MOVES JOURNAL IJOSCIENCE, 2024. Verfasst von Sumit Kumar Soni und 1 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study presents the study on intrusion detection in IoT networks that focuses on botnet attacks based on IoT device vulnerabilities. The proposed research will use a hybrid DL approach with architectures such as CNN2D-LSTM, DNN-LSTM, RNN, and RNN+FSA to enhance botnet attack detection on the N-BaIoT dataset. The optimized feature dimensionality is achieved without sacrificing performance by combining the strength of long-term dependency recognition with local pattern detection. A small labelled test set was developed to streamline the evaluation process, as well as to test how well the system works in comparison with attacks like Gafgyt and Mirai. The results from the RNN+FSA hybrid model are very excellent with 100% accuracy, precision, recall, and F1-score; better than other DL models. This study helps bring to the fore how hybrid DL techniques may be applied to boost the security of IoT and sheds the approach toward robust scalability in real-world applications.
Zitieren
APA
Soni, S. K., & Nair, S. (2024). Integrating Deep Learning with IOT: Combined Strategies for Botnet Detection. SMART MOVES JOURNAL IJOSCIENCE. https://doi.org/10.24113/ijoscience.v10i9.487
Vancouver
Soni SK, Nair S. Integrating Deep Learning with IOT: Combined Strategies for Botnet Detection. SMART MOVES JOURNAL IJOSCIENCE. 2024. doi:10.24113/ijoscience.v10i9.487
BibTeX
@article{Soni2024,
author = {Soni, Sumit Kumar and Nair, Sreeja},
title = {Integrating Deep Learning with IOT: Combined Strategies for Botnet Detection},
journal = {SMART MOVES JOURNAL IJOSCIENCE},
year = {2024},
doi = {10.24113/ijoscience.v10i9.487}
}
EUVIMED