ABSTRACT
Internet of Things (IoT) networks are vulnerable to intrusion attacks, which are unauthorized actions targeting IoT devices, networks, or ecosystems to disrupt the system's integrity. So, an Intrusion Detection System (IDS) is crucial to overcome the unique challenges of IoT environments, including heterogeneity of devices, resource constraints, and the evolving nature of security threats. Therefore, this paper proposes detecting the IoT network intrusion using a Modified Recurrent Neural Network (MRNN) with Firefly Algorithm (FA) optimization. After that, the classification method of MRNN is employed to detect the IOT intrusion with higher accuracy and lower computational complexity. FA that reduces the time required to solve complicated multiparameter problems. With a classification accuracy of 98% and a precision of 97%, the experiment's results demonstrated that the method is more successful than the current methods.
