A Framework for DDoS Attack Detection and Mitigation in IoT Networks Using Deep Learning

Internet of Things (IoT) devices have become popular in the present scenario. At the same time, they have become highly prone to exploitation due to their vulnerabilities and limited resources. There has also been an exponential rise in Distributed Denial of Service (DDoS) attacks among heterogeneous networks of IoT devices. It is very important to detect and mitigate the attack with a minimum amount of time to minimize loss. The proposed framework uses Lyrebird Armadillo Fusion Algorithm (LAFA) to select optimal features. IoT Guard presents the Capsule Gated Perception (CGP) model, a deep learning model that combines an optimized Multi-Layer Perceptron (MLP), Gated Repetitive Units (GRU), and Capsule Systems for attack detection. Deep-Q Networks are used for attack mitigation, ensuring security of the IoT devices. The implementation on two datasets illustrated that the proposed framework achieved better performance metrics and minimized false positives. The proposed framework paves the path for developing a secured IoT networks also the need for further research on minimizing Zero-day attacks and evolving vulnerabilities.