Distributed optimization for IoT attack detection using federated learning and Siberian Tiger optimizer
The rapid growth of IoT devices has heightened the risk of botnet attacks, calling for scalable and distributed detection solutions. In this context, this study proposes a distributed optimization system for IoT attack detection using CNN model utilizing federated learning. After optimizing the hyperparameters of the model at the server, the Siberian Tiger Optimization (STO) method distributes these values to clients for dispersed training. Our model achieves accuracy, recall, and precision of 0.89978, 0.94355, and 0.94455, respectively, using the N-BaIoT dataset. These findings show, in spite of latency issues, the efficiency of federated learning in distributed IoT security systems.
Authors
- Akshat Gaurav (ORCID: https://orcid.org/0000-0002-5796-9424)
- Wadee Alhalabi (ORCID: https://orcid.org/0000-0002-4505-7268)
- Brij B. Gupta (ORCID: https://orcid.org/0000-0003-4929-4698)
- Eaman Alharbi (ORCID: https://orcid.org/0000-0002-7970-3248)
- Kwok Tai Chui (ORCID: https://orcid.org/0000-0001-7992-9901)
- Varsha Arya (ORCID: https://orcid.org/0000-0001-7549-4429)
Institutions
- Asia University (TW)
- China Medical University (TW)
- King Abdulaziz University (SA)
- Symbiosis International University (IN)
- China Medical University Hospital (TW)
- Ronin Institute (US)
- Metropolitan University (BD)
- University of Petroleum and Energy Studies (IN)
- University of Hong Kong (HK)
Publication Details
- Journal
- ICT Express
- Published
- 2025-03-07
- DOI
- https://doi.org/10.1016/j.icte.2025.02.012
- Citations
- 3
- Primary Topic
- Network Security and Intrusion Detection
- Type
- article
- Field-Weighted Citation Impact
- 4.46