2024/03/16 by Ghazaleh Shirvani, Shirvani, Ghazaleh, Saeid Ghasemshirazi +3
Computer Science · #Advanced Malware Detection Techniques #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Internet Traffic Analysis and Secure E-voting #Machine Learning (cs.LG) #Network Security and Intrusion Detection
paper · pdf · doi:10.48550/arxiv.2403.10968
openalex publication_date 2024/03/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The rapid proliferation of the Internet of Things (IoT) has ushered in transformative connectivity between physical devices and the digital realm. Nonetheless, the escalating threat of Distributed Denial of Service (DDoS) attacks jeopardizes the integrity and reliability of IoT networks. Conventional DDoS mitigation approaches are ill-equipped to handle the intricacies of IoT ecosystems, potentially compromising data privacy. This paper introduces an innovative strategy to bolster the security of IoT networks against DDoS attacks by harnessing the power of Federated Learning that allows multiple IoT devices or edge nodes to collaboratively build a global model while preserving data privacy and minimizing communication overhead. The research aims to investigate Federated Learning's effectiveness in detecting and mitigating DDoS attacks in IoT. Our proposed framework leverages IoT devices' collective intelligence for real-time attack detection without compromising sensitive data. This study proposes innovative deep autoencoder approaches for data dimensionality reduction, retraining, and partial selection to enhance the performance and stability of the proposed model. Additionally, two renowned aggregation algorithms, FedAvg and FedAvgM, are employed in this research. Various metrics, including true positive rate, false positive rate, and F1-score, are employed to evaluate the model. The dataset utilized in this research, N-BaIoT, exhibits non-IID data distribution, where data categories are distributed quite differently. The negative impact of these distribution disparities is managed by employing retraining and partial selection techniques, enhancing the final model's stability. Furthermore, evaluation results demonstrate that the FedAvgM aggregation algorithm outperforms FedAvg, indicating that in non-IID datasets, FedAvgM provides better stability and performance.