FLBC-IDS: a federated learning and blockchain-based intrusion detection system for secure IoT environments

FLBC-IDS: a federated learning and blockchain-based intrusion detection system for secure IoT environments

연구 분야: Cryptography

학회: Multimedia Tools and Applications

The development of the Internet of Things (IoT) in multiple sectors has led to substantial security issues due to its decentralized structure and resource limits. To solve these problems, this paper proposes a novel technique called FLBC-IDS, which combines Horizontal Federated Learning (HFL), Hyperledger Blockchain, and EfficientNet to detect intrusions in IoT environments. The FLBC-IDS model uses HFL to enable secure and privacy-preserving model training across numerous IoT devices, resulting in decentralized data privacy and resource efficiency. The model's integration of Hyperledger Blockchain ensures tamper-resistant and transparent recording of model updates and agreements among participating IoT nodes, protecting the system's integrity. Furthermore, EfficientNet improves the model's robustness by effectively obtaining and categorizing features from network traffic data. On the CICIDS-2018 and CICIoT-2023 datasets, the FLBC-IDS model outperforms previous techniques in terms of accuracy, recall, F1-score, and precision. The FLBC-IDS model has an accuracy of 98.89%, recall of 98.044%, F1-score of 98.29%, and precision of 98.44%. The article analyzes the suggested model's merits and limitations, as well as future research directions for real-world deployment of IoT security solutions. Overall, the FLBC-IDS paradigm holds significant promise for improving IoT security and safeguarding IoT settings from infiltration attempts and cyber threats.