An optimal secure defense mechanism for DDoS attack in IoT network using feature optimization and intrusion detection system.

The article focuses on the development of an optimal secure defense mechanism for distributed denial-of-service (DDoS) attacks in Internet of Things (IoT) networks, named OSD-IDS, which integrates feature optimization and an intrusion detection system (IDS). The proposed OSD-IDS employs an enhanced ResNet architecture for deep feature extraction, an improved quantum query optimization (IQQO) algorithm for selecting optimal features to reduce data dimensionality, and a hybrid deep learning model combining convolutional neural network (CNN) and diagonal XG boosting (CNN-DigXG) for fast and accurate intrusion detection. Validation on benchmark datasets BoNeSi-SlowHTTPtest and CIC-DDoS2019 demonstrates that OSD-IDS achieves high detection accuracy (approximately 99.5% and 99.1%, respectively) and outperforms existing IDS methods across multiple performance metrics. The study concludes that OSD-IDS effectively addresses IoT-specific security challenges and suggests future extensions for smart healthcare applications and further optimization of feature selection algorithms.