Abstract: In recent decade, the security threats poses a high risk in an organization, which is associated with the proliferation of IoT devicesand increasing organizational assets. This ensures that the organization is unaware of the IoT devices connection with their own network. In such cases, security and integrity of network might pose a serious security threat to the network communications. In this paper, capsule network, which is an improved version of Convolutional Neural Network (CNN) is used to monitor the network traffic to identify accurately the trusted devices connected to the home network. Inadequacy of CNN in identifying the IoT devices during its communication in the network has made the present research to choose Capsule Networks (CapsNet) for device identification. Capsule network carries out the operation in an iterative manner in order to attain improved classification of IoT devices. The activation function used in the capsule network is a squash function that normalizes the magnitude of vector rather than the conventional usage of scalar elements. The outputs of activation function helps to find the trusted IoT devices through different capsules, which are formally trained using various concepts. The capsule network performs the identification of IoT devices and classifies the trusted and nontrusted devices based on the labeled network traffic data. The simulation is performed by the computation of collected labeled network data from IoT associated network.