A Novel Federated Edge Learning Approach for Detecting Cyberattacks in IoT Infrastructures
Sidra Abbas, Abdullah Al Hejaili, Gabriel Avelino Sampedro, Mideth Abisado, Ahmad Almadhor, Tariq Shahzad, Khmaies Ouahada
Abstract
The advancement of the communications system has resulted in the rise of the Internet of Things (IoT), which has increased the importance of cybersecurity research. IoT, which incorporates a range of gadgets into networks to offer complex and intelligent services, must maintain user privacy and deal with attacks such as spoofing, denial of service (DoS), jamming, and eavesdropping. Attacks change with time, and new ones develop every day. Numerous researchers look into IoT system attack models and evaluate machine learning, deep learning, and federated learning-based IoT security solutions. However, present methods usually require to produce reliable and encouraging results. Therefore, this study proposes a methodology for leveraging federated learning to identify large attacks on IoT devices using the novel CIC_IoT 2023 dataset. The method uses a federated deep neural network to achieve precise categorization. Before model training, the data was preprocessed using various data preparation techniques to guarantee the creation of a trustworthy dataset for categorization. The suggested method involves feature normalization, data balancing, and model prediction utilizing federated learning. The experimental findings show that the proposed method attained an exceptional accuracy of 99.00%, endorsing it for attack detection.