Abstract

The proliferation of Internet of Things (IoT) devices has introduced significant security challenges, making IoT networks increasingly vulnerable to diverse cyberattacks. Traditional intrusion detection systems (IDS) often struggle to adapt to the dynamic and heterogeneous nature of IoT environments, requiring centralized data processing that raises privacy concerns. This paper proposes an adaptive intrusion detection system (A-IDS) that leverages federated learning (FL) and blockchain-based trust management to enhance security in IoT networks. The A-IDS utilizes FL to train a global intrusion detection model collaboratively across multiple IoT devices without sharing raw data, preserving data privacy. Furthermore, a blockchain-based trust management system is integrated to ensure the integrity of the FL process and mitigate potential attacks from malicious participants. The proposed system is evaluated through extensive simulations using a realistic IoT network scenario. The results demonstrate that the A-IDS achieves high detection accuracy while maintaining data privacy and resilience against adversarial attacks, offering a promising solution for securing IoT environments. The system's performance is compared against existing centralized and decentralized approaches, highlighting its advantages in terms of accuracy, privacy, and robustness.